Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 629 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.4323. Min Act: -0.1700
Data Index: 7946104 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.3698. Min Act: -0.1700
Data Index: 6397899 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.4323. Min Act: -0.1700
Data Index: 2290752 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.3073. Min Act: -0.1700
Data Index: 375366 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1823. Min Act: -0.1700
Data Index: 7849584 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.2448. Min Act: -0.1700
Data Index: 5879755 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1823. Min Act: -0.1700
Data Index: 2013960 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1198. Min Act: -0.1700
Data Index: 3130418 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1198. Min Act: -0.1700
Data Index: 8816871 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1823. Min Act: -0.1700
Data Index: 1967560 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.0573. Min Act: -0.1700
Data Index: 416021 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.1198. Min Act: -0.1700
Data Index: 4631381 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.0573. Min Act: -0.1700
Data Index: 7991325 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.0573. Min Act: -0.1700
Data Index: 2364861 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4323. Min Range: -11.4323
Max Act: 10.9948. Min Act: -0.1700
Data Index: 5264120 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4323. Min Range: -11.4323
Max Act: 10.9948. Min Act: -0.1700
Data Index: 86407 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4323. Min Range: -11.4323
Max Act: 11.0573. Min Act: -0.1700
Data Index: 3157011 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4323. Min Range: -11.4323
Max Act: 10.9948. Min Act: -0.1700
Data Index: 3117818 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4323. Min Range: -11.4323
Max Act: 10.9323. Min Act: -0.1700
Data Index: 7387484 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4323. Min Range: -11.4323
Max Act: 10.9323. Min Act: -0.1700
Data Index: 5920641 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19