Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8876. Min Act: -0.1700
Data Index: 5313316 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8876. Min Act: -0.1700
Data Index: 8086816 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8564. Min Act: -0.1700
Data Index: 5203627 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8564. Min Act: -0.1700
Data Index: 6238817 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8251. Min Act: -0.1700
Data Index: 7886820 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.8251. Min Act: -0.1700
Data Index: 8676664 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7626. Min Act: -0.1700
Data Index: 6517509 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7626. Min Act: -0.1700
Data Index: 3201966 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7001. Min Act: -0.1700
Data Index: 7585197 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7314. Min Act: -0.1700
Data Index: 2793989 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7314. Min Act: -0.1700
Data Index: 2254216 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.7001. Min Act: -0.1700
Data Index: 106463 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6689. Min Act: -0.1700
Data Index: 4097219 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6689. Min Act: -0.1700
Data Index: 355735 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6689. Min Act: -0.1700
Data Index: 3091002 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6064. Min Act: -0.1700
Data Index: 2676671 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6376. Min Act: -0.1700
Data Index: 3757666 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6376. Min Act: -0.1700
Data Index: 6706033 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6376. Min Act: -0.1700
Data Index: 990676 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8876. Min Range: -6.8876
Max Act: 6.6064. Min Act: -0.1700
Data Index: 4667823 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19