Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1604 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 7.4148. Min Range: -7.4148
Max Act: 7.4148. Min Act: -0.1700
Data Index: 827049 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.3211. Min Act: -0.1700
Data Index: 5695994 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.3523. Min Act: -0.1700
Data Index: 7344139 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.3523. Min Act: -0.1700
Data Index: 1276511 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.2898. Min Act: -0.1700
Data Index: 7023886 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1961. Min Act: -0.1700
Data Index: 4452409 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.2586. Min Act: -0.1700
Data Index: 6935016 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.2273. Min Act: -0.1700
Data Index: 101823 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1961. Min Act: -0.1700
Data Index: 7297926 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1648. Min Act: -0.1700
Data Index: 792096 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1336. Min Act: -0.1700
Data Index: 1780276 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1648. Min Act: -0.1700
Data Index: 7255601 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1023. Min Act: -0.1700
Data Index: 2635926 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.0711. Min Act: -0.1700
Data Index: 6735632 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1023. Min Act: -0.1700
Data Index: 7337871 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.0711. Min Act: -0.1700
Data Index: 7536169 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.1023. Min Act: -0.1700
Data Index: 2959975 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.0398. Min Act: -0.1700
Data Index: 7366880 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.0711. Min Act: -0.1700
Data Index: 2036230 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4148. Min Range: -7.4148
Max Act: 6.0398. Min Act: -0.1700
Data Index: 81840 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19