Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1397. Min Range: -4.1397
Max Act: 4.1397. Min Act: -0.1700
Data Index: 5328657 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1397. Min Range: -4.1397
Max Act: 4.1084. Min Act: -0.1700
Data Index: 7499219 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1397. Min Range: -4.1397
Max Act: 4.1084. Min Act: -0.1700
Data Index: 190221 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1397. Min Range: -4.1397
Max Act: 4.0146. Min Act: -0.1700
Data Index: 6939364 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.9209. Min Act: -0.1700
Data Index: 4877942 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.8583. Min Act: -0.1700
Data Index: 4946268 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7958. Min Act: -0.1700
Data Index: 1290254 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7958. Min Act: -0.1700
Data Index: 2367220 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7801. Min Act: -0.1700
Data Index: 6012631 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7801. Min Act: -0.1700
Data Index: 8518018 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7801. Min Act: -0.1700
Data Index: 8676845 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7801. Min Act: -0.1700
Data Index: 8336955 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7801. Min Act: -0.1700
Data Index: 6413745 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7645. Min Act: -0.1700
Data Index: 5681780 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7645. Min Act: -0.1700
Data Index: 733259 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7645. Min Act: -0.1700
Data Index: 4589686 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7489. Min Act: -0.1700
Data Index: 2580614 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7489. Min Act: -0.1700
Data Index: 480598 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7489. Min Act: -0.1700
Data Index: 4741756 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1397. Min Range: -4.1397
Max Act: 3.7489. Min Act: -0.1700
Data Index: 604546 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19