Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.7226. Min Act: -0.1700
Data Index: 7320811 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.4722. Min Act: -0.1700
Data Index: 4952587 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.4252. Min Act: -0.1700
Data Index: 7204255 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.3468. Min Act: -0.1700
Data Index: 8323434 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.3468. Min Act: -0.1700
Data Index: 1976918 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.3311. Min Act: -0.1700
Data Index: 677538 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.3154. Min Act: -0.1700
Data Index: 1485803 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2840. Min Act: -0.1700
Data Index: 2334422 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2997. Min Act: -0.1700
Data Index: 2921113 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2526. Min Act: -0.1700
Data Index: 3677719 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2683. Min Act: -0.1700
Data Index: 4762889 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2683. Min Act: -0.1700
Data Index: 4515957 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2211. Min Act: -0.1700
Data Index: 2283261 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2211. Min Act: -0.1700
Data Index: 2316501 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2054. Min Act: -0.1700
Data Index: 1316889 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2054. Min Act: -0.1700
Data Index: 1612964 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.2054. Min Act: -0.1700
Data Index: 2037462 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.1740. Min Act: -0.1700
Data Index: 743659 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.1897. Min Act: -0.1700
Data Index: 5470601 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7226. Min Range: -3.7226
Max Act: 3.1897. Min Act: -0.1700
Data Index: 3734043 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19