Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2173 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.8975. Min Act: -0.1700
Data Index: 1650133 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.7725. Min Act: -0.1700
Data Index: 3302248 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.7100. Min Act: -0.1700
Data Index: 2829312 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.7412. Min Act: -0.1700
Data Index: 3600294 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.7100. Min Act: -0.1700
Data Index: 2444750 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.6787. Min Act: -0.1700
Data Index: 4314295 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.6475. Min Act: -0.1700
Data Index: 7811980 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.6787. Min Act: -0.1700
Data Index: 713806 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 3082281 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 2615517 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 6553127 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.6162. Min Act: -0.1700
Data Index: 209878 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 2771553 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 516865 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.6162. Min Act: -0.1700
Data Index: 526514 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5850. Min Act: -0.1700
Data Index: 1210623 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5537. Min Act: -0.1700
Data Index: 796943 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5537. Min Act: -0.1700
Data Index: 5022935 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5537. Min Act: -0.1700
Data Index: 5976413 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8975. Min Range: -6.8975
Max Act: 6.5537. Min Act: -0.1700
Data Index: 3447942 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19