Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0787. Min Range: -7.0787
Max Act: 7.0787. Min Act: -0.1700
Data Index: 7875897 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.8287. Min Act: -0.1700
Data Index: 6688393 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.7974. Min Act: -0.1700
Data Index: 8578604 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6724. Min Act: -0.1700
Data Index: 2826327 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.7037. Min Act: -0.1700
Data Index: 8741997 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6412. Min Act: -0.1700
Data Index: 3848738 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6099. Min Act: -0.1700
Data Index: 6261257 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6099. Min Act: -0.1700
Data Index: 5837902 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6099. Min Act: -0.1700
Data Index: 6308398 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.6099. Min Act: -0.1700
Data Index: 396060 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5787. Min Act: -0.1700
Data Index: 5256884 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5787. Min Act: -0.1700
Data Index: 8742002 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5474. Min Act: -0.1700
Data Index: 7798279 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5474. Min Act: -0.1700
Data Index: 6266100 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5162. Min Act: -0.1700
Data Index: 3892235 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.4849. Min Act: -0.1700
Data Index: 3864966 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.4849. Min Act: -0.1700
Data Index: 5198528 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.5162. Min Act: -0.1700
Data Index: 40104 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.4537. Min Act: -0.1700
Data Index: 2072144 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0787. Min Range: -7.0787
Max Act: 6.4224. Min Act: -0.1700
Data Index: 5883693 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19