Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.7488. Min Act: -0.1700
Data Index: 6145004 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.6238. Min Act: -0.1700
Data Index: 3170988 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.5925. Min Act: -0.1700
Data Index: 5505889 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.5925. Min Act: -0.1700
Data Index: 5469216 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.5300. Min Act: -0.1700
Data Index: 2090635 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4988. Min Act: -0.1700
Data Index: 4723117 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4675. Min Act: -0.1700
Data Index: 2380001 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.4050. Min Act: -0.1700
Data Index: 8733941 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3425. Min Act: -0.1700
Data Index: 3547228 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 1037535 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 6800392 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 290771 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5634406 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5508831 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 6092374 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3738. Min Act: -0.1700
Data Index: 8106979 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3425. Min Act: -0.1700
Data Index: 7723375 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3113. Min Act: -0.1700
Data Index: 671591 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3113. Min Act: -0.1700
Data Index: 1734103 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7488. Min Range: -6.7488
Max Act: 6.3425. Min Act: -0.1700
Data Index: 1531323 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19