Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2925 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.9635. Min Act: -0.1700
Data Index: 8165367 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.8385. Min Act: -0.1700
Data Index: 2379547 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.8385. Min Act: -0.1700
Data Index: 8343601 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.7135. Min Act: -0.1700
Data Index: 5594560 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6510. Min Act: -0.1700
Data Index: 5454141 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6510. Min Act: -0.1700
Data Index: 5712916 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6510. Min Act: -0.1700
Data Index: 2595125 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6510. Min Act: -0.1700
Data Index: 7538722 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6198. Min Act: -0.1700
Data Index: 214725 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.6198. Min Act: -0.1700
Data Index: 3752987 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5885. Min Act: -0.1700
Data Index: 572672 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5885. Min Act: -0.1700
Data Index: 601702 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5885. Min Act: -0.1700
Data Index: 6457843 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5573. Min Act: -0.1700
Data Index: 4741725 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5573. Min Act: -0.1700
Data Index: 236069 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2521996 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5260. Min Act: -0.1700
Data Index: 2226480 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5260. Min Act: -0.1700
Data Index: 698807 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5260. Min Act: -0.1700
Data Index: 716638 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9635. Min Range: -4.9635
Max Act: 4.5260. Min Act: -0.1700
Data Index: 41006 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19