Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7443. Min Range: -6.7443
Max Act: 6.7443. Min Act: -0.1700
Data Index: 1163147 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7443. Min Range: -6.7443
Max Act: 6.1193. Min Act: -0.1700
Data Index: 2644602 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7443. Min Range: -6.7443
Max Act: 6.0881. Min Act: -0.1700
Data Index: 3537352 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7443. Min Range: -6.7443
Max Act: 6.0256. Min Act: -0.1700
Data Index: 5433689 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.9943. Min Act: -0.1700
Data Index: 2912129 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.9318. Min Act: -0.1700
Data Index: 24320 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8693. Min Act: -0.1700
Data Index: 5490164 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8693. Min Act: -0.1700
Data Index: 4512190 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8381. Min Act: -0.1700
Data Index: 7260806 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8381. Min Act: -0.1700
Data Index: 5893119 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8381. Min Act: -0.1700
Data Index: 8149829 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8381. Min Act: -0.1700
Data Index: 7266767 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8381. Min Act: -0.1700
Data Index: 6277365 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 3198616 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 2623223 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.7756. Min Act: -0.1700
Data Index: 4384215 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.7756. Min Act: -0.1700
Data Index: 6591249 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.7756. Min Act: -0.1700
Data Index: 3398736 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.7443. Min Act: -0.1700
Data Index: 365901 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7443. Min Range: -6.7443
Max Act: 5.7443. Min Act: -0.1700
Data Index: 489986 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19