Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.8381. Min Act: -0.1700
Data Index: 5712920 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.7444. Min Act: -0.1700
Data Index: 240508 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.6819. Min Act: -0.1700
Data Index: 4147648 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.6506. Min Act: -0.1700
Data Index: 3883112 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.6194. Min Act: -0.1700
Data Index: 3832767 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.5569. Min Act: -0.1700
Data Index: 463418 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.5256. Min Act: -0.1700
Data Index: 8695289 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.4944. Min Act: -0.1700
Data Index: 7106877 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.4631. Min Act: -0.1700
Data Index: 1059903 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.4319. Min Act: -0.1700
Data Index: 6120796 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3694. Min Act: -0.1700
Data Index: 5785999 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.4006. Min Act: -0.1700
Data Index: 4926070 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3381. Min Act: -0.1700
Data Index: 7770013 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3694. Min Act: -0.1700
Data Index: 1894324 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3381. Min Act: -0.1700
Data Index: 4874496 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3069. Min Act: -0.1700
Data Index: 7852553 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3069. Min Act: -0.1700
Data Index: 4540278 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3069. Min Act: -0.1700
Data Index: 1715497 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.3069. Min Act: -0.1700
Data Index: 1066078 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8381. Min Range: -6.8381
Max Act: 6.2756. Min Act: -0.1700
Data Index: 8173620 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19