Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1626 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.7817. Min Act: -0.1700
Data Index: 5645657 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.5005. Min Act: -0.1700
Data Index: 7188574 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.4067. Min Act: -0.1700
Data Index: 6315715 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.4380. Min Act: -0.1700
Data Index: 7188588 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3755. Min Act: -0.1700
Data Index: 3316308 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3755. Min Act: -0.1700
Data Index: 5929166 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3442. Min Act: -0.1700
Data Index: 3447571 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3442. Min Act: -0.1700
Data Index: 4065583 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3442. Min Act: -0.1700
Data Index: 8171931 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3130. Min Act: -0.1700
Data Index: 8051084 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3130. Min Act: -0.1700
Data Index: 3748292 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3130. Min Act: -0.1700
Data Index: 4877162 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.3130. Min Act: -0.1700
Data Index: 678793 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2505. Min Act: -0.1700
Data Index: 15059 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2505. Min Act: -0.1700
Data Index: 4241741 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2817. Min Act: -0.1700
Data Index: 7188573 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2817. Min Act: -0.1700
Data Index: 1771878 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2505. Min Act: -0.1700
Data Index: 7131352 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2505. Min Act: -0.1700
Data Index: 938627 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7817. Min Range: -4.7817
Max Act: 4.2192. Min Act: -0.1700
Data Index: 3748287 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19