Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0398. Min Range: -3.0398
Max Act: 3.0398. Min Act: -0.1700
Data Index: 5759680 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0398. Min Range: -3.0398
Max Act: 3.0082. Min Act: -0.1700
Data Index: 7688091 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8974. Min Act: -0.1700
Data Index: 5950690 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8974. Min Act: -0.1700
Data Index: 980143 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8498. Min Act: -0.1700
Data Index: 6180567 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8339. Min Act: -0.1700
Data Index: 2855996 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8180. Min Act: -0.1700
Data Index: 8306183 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8180. Min Act: -0.1700
Data Index: 2504895 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8180. Min Act: -0.1700
Data Index: 7335960 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7861. Min Act: -0.1700
Data Index: 4792223 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.8020. Min Act: -0.1700
Data Index: 548428 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7861. Min Act: -0.1700
Data Index: 6549107 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7861. Min Act: -0.1700
Data Index: 433296 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7702. Min Act: -0.1700
Data Index: 7148565 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7702. Min Act: -0.1700
Data Index: 2397036 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7702. Min Act: -0.1700
Data Index: 5184029 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7542. Min Act: -0.1700
Data Index: 7195222 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7542. Min Act: -0.1700
Data Index: 5546215 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7702. Min Act: -0.1700
Data Index: 471092 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0398. Min Range: -3.0398
Max Act: 2.7383. Min Act: -0.1700
Data Index: 5893389 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19