Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2445 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2299. Min Range: -9.2299
Max Act: 9.2299. Min Act: -0.1700
Data Index: 4035583 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2299. Min Range: -9.2299
Max Act: 9.1049. Min Act: -0.1700
Data Index: 1984553 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2299. Min Range: -9.2299
Max Act: 9.1049. Min Act: -0.1700
Data Index: 1334645 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2299. Min Range: -9.2299
Max Act: 9.0424. Min Act: -0.1700
Data Index: 1334638 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2299. Min Range: -9.2299
Max Act: 9.0424. Min Act: -0.1700
Data Index: 1334637 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.9799. Min Act: -0.1700
Data Index: 1334647 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.9174. Min Act: -0.1700
Data Index: 1334644 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.8549. Min Act: -0.1700
Data Index: 4397785 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.8549. Min Act: -0.1700
Data Index: 8744102 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.7924. Min Act: -0.1700
Data Index: 1334636 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.7299. Min Act: -0.1700
Data Index: 1334648 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.7299. Min Act: -0.1700
Data Index: 1334642 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.7299. Min Act: -0.1700
Data Index: 1334643 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.6674. Min Act: -0.1700
Data Index: 1873701 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.6674. Min Act: -0.1700
Data Index: 6394806 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.6674. Min Act: -0.1700
Data Index: 5852682 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.6049. Min Act: -0.1700
Data Index: 1334640 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.6049. Min Act: -0.1700
Data Index: 3421154 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.5424. Min Act: -0.1700
Data Index: 5535063 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2299. Min Range: -9.2299
Max Act: 8.5424. Min Act: -0.1700
Data Index: 1334641 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19