Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4069 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0692. Min Range: -8.0692
Max Act: 8.0692. Min Act: -0.1700
Data Index: 4863790 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0692. Min Range: -8.0692
Max Act: 8.0067. Min Act: -0.1700
Data Index: 4851681 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0692. Min Range: -8.0692
Max Act: 8.0692. Min Act: -0.1700
Data Index: 4804942 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0692. Min Range: -8.0692
Max Act: 8.0067. Min Act: -0.1700
Data Index: 6334825 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 6593286 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 1765421 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 3445444 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 3445439 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.9442. Min Act: -0.1700
Data Index: 3385056 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 7138366 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 2573018 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 1324362 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8817. Min Act: -0.1700
Data Index: 3070115 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8192. Min Act: -0.1700
Data Index: 13677 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.8192. Min Act: -0.1700
Data Index: 3355720 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 3260988 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 3881766 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.7567. Min Act: -0.1700
Data Index: 7292149 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.6942. Min Act: -0.1700
Data Index: 7677397 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0692. Min Range: -8.0692
Max Act: 7.6942. Min Act: -0.1700
Data Index: 569172 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19