Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.8077. Min Act: -0.1700
Data Index: 1464147 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.7452. Min Act: -0.1700
Data Index: 8822425 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.7139. Min Act: -0.1700
Data Index: 2180043 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.6202. Min Act: -0.1700
Data Index: 5086925 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.6514. Min Act: -0.1700
Data Index: 1735628 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.5577. Min Act: -0.1700
Data Index: 2938787 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.4952. Min Act: -0.1700
Data Index: 6141085 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.4952. Min Act: -0.1700
Data Index: 8757503 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.4952. Min Act: -0.1700
Data Index: 3619159 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.4327. Min Act: -0.1700
Data Index: 6342906 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.4014. Min Act: -0.1700
Data Index: 625674 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3702. Min Act: -0.1700
Data Index: 2941050 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3389. Min Act: -0.1700
Data Index: 4294552 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3389. Min Act: -0.1700
Data Index: 6314751 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3389. Min Act: -0.1700
Data Index: 107875 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3077. Min Act: -0.1700
Data Index: 8548855 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3077. Min Act: -0.1700
Data Index: 4949692 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.2764. Min Act: -0.1700
Data Index: 8668857 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3077. Min Act: -0.1700
Data Index: 4757385 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8077. Min Range: -6.8077
Max Act: 6.3077. Min Act: -0.1700
Data Index: 6289173 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19