Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4958 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.7911. Min Act: -0.1700
Data Index: 3776288 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.6661. Min Act: -0.1700
Data Index: 8246408 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.6973. Min Act: -0.1700
Data Index: 3030378 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.5098. Min Act: -0.1700
Data Index: 6917994 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.4786. Min Act: -0.1700
Data Index: 6287219 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.4786. Min Act: -0.1700
Data Index: 750025 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.3536. Min Act: -0.1700
Data Index: 8663792 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.3536. Min Act: -0.1700
Data Index: 2974324 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.3536. Min Act: -0.1700
Data Index: 2216809 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.3223. Min Act: -0.1700
Data Index: 4660299 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.3223. Min Act: -0.1700
Data Index: 6301271 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2911. Min Act: -0.1700
Data Index: 6078861 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2911. Min Act: -0.1700
Data Index: 4848100 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 1128774 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 2895858 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 1107091 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 4325780 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 7482994 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2598. Min Act: -0.1700
Data Index: 1839371 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7911. Min Range: -6.7911
Max Act: 6.2286. Min Act: -0.1700
Data Index: 6076816 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19