Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4176 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0695. Min Range: -7.0695
Max Act: 7.0695. Min Act: -0.1700
Data Index: 4781908 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.9757. Min Act: -0.1700
Data Index: 8650280 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.9445. Min Act: -0.1700
Data Index: 2741333 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.8820. Min Act: -0.1700
Data Index: 1887933 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.7570. Min Act: -0.1700
Data Index: 7497360 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.7570. Min Act: -0.1700
Data Index: 3282345 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.7570. Min Act: -0.1700
Data Index: 6386447 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.7570. Min Act: -0.1700
Data Index: 6547288 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6945. Min Act: -0.1700
Data Index: 7184761 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6945. Min Act: -0.1700
Data Index: 4602521 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6632. Min Act: -0.1700
Data Index: 6562139 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6945. Min Act: -0.1700
Data Index: 614029 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6632. Min Act: -0.1700
Data Index: 237740 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6007. Min Act: -0.1700
Data Index: 8659844 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6007. Min Act: -0.1700
Data Index: 7171028 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.6007. Min Act: -0.1700
Data Index: 1622636 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.5695. Min Act: -0.1700
Data Index: 6506642 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.5695. Min Act: -0.1700
Data Index: 8244587 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.5070. Min Act: -0.1700
Data Index: 8030284 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0695. Min Range: -7.0695
Max Act: 6.5382. Min Act: -0.1700
Data Index: 1495166 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19