Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.8132. Min Act: -0.1700
Data Index: 341167 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.7507. Min Act: -0.1700
Data Index: 2078044 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.7507. Min Act: -0.1700
Data Index: 2899533 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.7507. Min Act: -0.1700
Data Index: 3556924 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6882. Min Act: -0.1700
Data Index: 4546965 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6569. Min Act: -0.1700
Data Index: 3468517 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.7194. Min Act: -0.1700
Data Index: 4016903 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6569. Min Act: -0.1700
Data Index: 7389285 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6882. Min Act: -0.1700
Data Index: 5694119 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6569. Min Act: -0.1700
Data Index: 3241562 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6882. Min Act: -0.1700
Data Index: 7640437 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 8556438 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 7918433 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 5708142 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 8815830 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 6279500 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 770740 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.6257. Min Act: -0.1700
Data Index: 7087923 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5944. Min Act: -0.1700
Data Index: 7498070 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8132. Min Range: -5.8132
Max Act: 5.5944. Min Act: -0.1700
Data Index: 2124664 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19