Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.4264. Min Act: -0.1700
Data Index: 4307367 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.3326. Min Act: -0.1700
Data Index: 4548164 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.3014. Min Act: -0.1700
Data Index: 3169959 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.2076. Min Act: -0.1700
Data Index: 2821965 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.1764. Min Act: -0.1700
Data Index: 114188 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4264. Min Range: -6.4264
Max Act: 6.0201. Min Act: -0.1700
Data Index: 6725187 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9889. Min Act: -0.1700
Data Index: 1700098 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9889. Min Act: -0.1700
Data Index: 8046215 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 1830833 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 6115952 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3988865 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 78087 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.9264. Min Act: -0.1700
Data Index: 4063404 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8951. Min Act: -0.1700
Data Index: 2095871 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8639. Min Act: -0.1700
Data Index: 3674818 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8326. Min Act: -0.1700
Data Index: 1366319 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8639. Min Act: -0.1700
Data Index: 7318176 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8639. Min Act: -0.1700
Data Index: 2787141 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8014. Min Act: -0.1700
Data Index: 2208005 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4264. Min Range: -6.4264
Max Act: 5.8326. Min Act: -0.1700
Data Index: 5981774 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19