Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 158 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.7320. Min Act: -0.1700
Data Index: 6966518 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6070. Min Act: -0.1700
Data Index: 4629053 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.6382. Min Act: -0.1700
Data Index: 6432494 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 4380601 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 7496026 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 2645402 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5445. Min Act: -0.1700
Data Index: 866152 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5757. Min Act: -0.1700
Data Index: 1039315 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5445. Min Act: -0.1700
Data Index: 3358736 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 366451 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 3960148 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 3504140 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 1534160 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 1481011 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.5132. Min Act: -0.1700
Data Index: 1160872 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 5719248 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 3438564 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 1383523 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4507. Min Act: -0.1700
Data Index: 1601585 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7320. Min Range: -4.7320
Max Act: 4.4820. Min Act: -0.1700
Data Index: 317441 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19