Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2836 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2420. Min Range: -3.2420
Max Act: 3.2420. Min Act: -0.1700
Data Index: 8543319 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2420. Min Range: -3.2420
Max Act: 3.0688. Min Act: -0.1700
Data Index: 5496177 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2420. Min Range: -3.2420
Max Act: 3.0688. Min Act: -0.1700
Data Index: 4284413 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.9740. Min Act: -0.1700
Data Index: 6033048 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.8631. Min Act: -0.1700
Data Index: 5675489 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.8631. Min Act: -0.1700
Data Index: 3659196 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.8631. Min Act: -0.1700
Data Index: 4524576 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.8313. Min Act: -0.1700
Data Index: 7709848 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7836. Min Act: -0.1700
Data Index: 3950729 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7037. Min Act: -0.1700
Data Index: 7709847 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7517. Min Act: -0.1700
Data Index: 1909812 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7676. Min Act: -0.1700
Data Index: 5567161 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7357. Min Act: -0.1700
Data Index: 3950730 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7197. Min Act: -0.1700
Data Index: 3288985 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7357. Min Act: -0.1700
Data Index: 4642489 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7517. Min Act: -0.1700
Data Index: 1450917 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7197. Min Act: -0.1700
Data Index: 2773955 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.7037. Min Act: -0.1700
Data Index: 4475955 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.6877. Min Act: -0.1700
Data Index: 7538908 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2420. Min Range: -3.2420
Max Act: 2.6877. Min Act: -0.1700
Data Index: 3793249 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19