Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3160 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9992. Min Act: -0.1700
Data Index: 2713678 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9367. Min Act: -0.1700
Data Index: 2713687 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 70759 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.9054. Min Act: -0.1700
Data Index: 8567596 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 6466196 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8742. Min Act: -0.1700
Data Index: 6961501 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8429. Min Act: -0.1700
Data Index: 4612803 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 7780045 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 3289277 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 5595834 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 5217589 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 7638881 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 5292143 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.8117. Min Act: -0.1700
Data Index: 388435 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7804. Min Act: -0.1700
Data Index: 3848 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7804. Min Act: -0.1700
Data Index: 5419494 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7804. Min Act: -0.1700
Data Index: 2242688 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7492. Min Act: -0.1700
Data Index: 126256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7492. Min Act: -0.1700
Data Index: 1397985 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9992. Min Range: -4.9992
Max Act: 4.7179. Min Act: -0.1700
Data Index: 7705254 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19