Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5805 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.4801. Min Act: -0.1700
Data Index: 609242 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.2926. Min Act: -0.1700
Data Index: 1833390 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.0739. Min Act: -0.1700
Data Index: 4913987 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.0426. Min Act: -0.1700
Data Index: 907760 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.0114. Min Act: -0.1700
Data Index: 7382400 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4801. Min Range: -6.4801
Max Act: 6.0114. Min Act: -0.1700
Data Index: 5595629 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.9489. Min Act: -0.1700
Data Index: 3387436 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.9489. Min Act: -0.1700
Data Index: 8657998 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.9176. Min Act: -0.1700
Data Index: 1743257 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.9176. Min Act: -0.1700
Data Index: 7424868 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8864. Min Act: -0.1700
Data Index: 177432 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8864. Min Act: -0.1700
Data Index: 2363857 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8864. Min Act: -0.1700
Data Index: 5842122 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8551. Min Act: -0.1700
Data Index: 2008462 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8551. Min Act: -0.1700
Data Index: 4305518 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8551. Min Act: -0.1700
Data Index: 1204158 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8239. Min Act: -0.1700
Data Index: 5732199 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.8239. Min Act: -0.1700
Data Index: 2854749 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.7614. Min Act: -0.1700
Data Index: 121793 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4801. Min Range: -6.4801
Max Act: 5.7614. Min Act: -0.1700
Data Index: 118335 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19