Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.4489. Min Act: -0.1700
Data Index: 5412870 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.4489. Min Act: -0.1700
Data Index: 338261 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.4489. Min Act: -0.1700
Data Index: 3955579 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.4176. Min Act: -0.1700
Data Index: 3857749 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.3551. Min Act: -0.1700
Data Index: 4737036 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.3551. Min Act: -0.1700
Data Index: 7976040 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.3239. Min Act: -0.1700
Data Index: 3853268 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.3239. Min Act: -0.1700
Data Index: 4033510 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.3239. Min Act: -0.1700
Data Index: 1345147 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 1118625 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 7030272 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 1818693 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 5785549 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 5664568 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2614. Min Act: -0.1700
Data Index: 7942311 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2926. Min Act: -0.1700
Data Index: 4351386 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.2301. Min Act: -0.1700
Data Index: 7853912 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.1989. Min Act: -0.1700
Data Index: 1172780 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.1989. Min Act: -0.1700
Data Index: 4492934 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4489. Min Range: -5.4489
Max Act: 5.1989. Min Act: -0.1700
Data Index: 2270406 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19