Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1903 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.6226. Min Act: -0.1700
Data Index: 431297 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.4976. Min Act: -0.1700
Data Index: 6436170 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.4663. Min Act: -0.1700
Data Index: 6309490 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3413. Min Act: -0.1700
Data Index: 8496128 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3101. Min Act: -0.1700
Data Index: 2993458 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3413. Min Act: -0.1700
Data Index: 563036 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3413. Min Act: -0.1700
Data Index: 1140906 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3101. Min Act: -0.1700
Data Index: 3710577 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.3101. Min Act: -0.1700
Data Index: 5630390 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2476. Min Act: -0.1700
Data Index: 7003304 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2476. Min Act: -0.1700
Data Index: 231781 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 4234078 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2476. Min Act: -0.1700
Data Index: 1742650 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 7509917 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 8062268 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 8221762 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 1081464 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.1851. Min Act: -0.1700
Data Index: 3612304 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 8434896 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6226. Min Range: -5.6226
Max Act: 5.2163. Min Act: -0.1700
Data Index: 6560212 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19