Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 736 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.5736. Min Act: -0.1700
Data Index: 4350848 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.5424. Min Act: -0.1700
Data Index: 7715819 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.5111. Min Act: -0.1700
Data Index: 5309638 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.4486. Min Act: -0.1700
Data Index: 812534 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.4174. Min Act: -0.1700
Data Index: 1823184 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.3861. Min Act: -0.1700
Data Index: 6611517 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.3549. Min Act: -0.1700
Data Index: 1660545 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.3236. Min Act: -0.1700
Data Index: 4520404 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2611. Min Act: -0.1700
Data Index: 8102771 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2924. Min Act: -0.1700
Data Index: 6399364 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.3236. Min Act: -0.1700
Data Index: 6138362 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2924. Min Act: -0.1700
Data Index: 2608031 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2924. Min Act: -0.1700
Data Index: 1929477 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2924. Min Act: -0.1700
Data Index: 2680148 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2611. Min Act: -0.1700
Data Index: 7057354 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2299. Min Act: -0.1700
Data Index: 5771421 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.2299. Min Act: -0.1700
Data Index: 6700890 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.1986. Min Act: -0.1700
Data Index: 2441534 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.1986. Min Act: -0.1700
Data Index: 5649814 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5736. Min Range: -6.5736
Max Act: 6.1674. Min Act: -0.1700
Data Index: 1708929 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19