Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.5796. Min Act: -0.1700
Data Index: 442969 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.4546. Min Act: -0.1700
Data Index: 3760087 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3608. Min Act: -0.1700
Data Index: 8693096 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3608. Min Act: -0.1700
Data Index: 1345377 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3921. Min Act: -0.1700
Data Index: 3162003 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.3296. Min Act: -0.1700
Data Index: 8472389 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2983. Min Act: -0.1700
Data Index: 1660893 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2671. Min Act: -0.1700
Data Index: 7591645 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2983. Min Act: -0.1700
Data Index: 8100430 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2671. Min Act: -0.1700
Data Index: 543970 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2671. Min Act: -0.1700
Data Index: 5788758 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6933413 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 2015000 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 4932116 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 6095839 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2358. Min Act: -0.1700
Data Index: 2882902 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 7736056 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 296633 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.2046. Min Act: -0.1700
Data Index: 1292834 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5796. Min Range: -5.5796
Max Act: 5.1733. Min Act: -0.1700
Data Index: 3430367 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19