Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0419. Min Range: -4.0419
Max Act: 4.0419. Min Act: -0.1700
Data Index: 1912608 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.7605. Min Act: -0.1700
Data Index: 2303159 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.7605. Min Act: -0.1700
Data Index: 3376821 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.7605. Min Act: -0.1700
Data Index: 2117134 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6979. Min Act: -0.1700
Data Index: 587709 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6666. Min Act: -0.1700
Data Index: 2627608 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6666. Min Act: -0.1700
Data Index: 2082637 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6353. Min Act: -0.1700
Data Index: 5019123 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6040. Min Act: -0.1700
Data Index: 1630434 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.6040. Min Act: -0.1700
Data Index: 4179854 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.5727. Min Act: -0.1700
Data Index: 4968323 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.5727. Min Act: -0.1700
Data Index: 5457520 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.5414. Min Act: -0.1700
Data Index: 8392491 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4944. Min Act: -0.1700
Data Index: 5115750 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4944. Min Act: -0.1700
Data Index: 3883076 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.5101. Min Act: -0.1700
Data Index: 8713105 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4788. Min Act: -0.1700
Data Index: 678085 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4944. Min Act: -0.1700
Data Index: 6995904 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4788. Min Act: -0.1700
Data Index: 4447805 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0419. Min Range: -4.0419
Max Act: 3.4788. Min Act: -0.1700
Data Index: 5970502 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19