Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2402 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0394. Min Range: -3.0394
Max Act: 3.0394. Min Act: -0.1700
Data Index: 4132544 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.8494. Min Act: -0.1700
Data Index: 4954505 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.7857. Min Act: -0.1700
Data Index: 2311583 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.7538. Min Act: -0.1700
Data Index: 4954519 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.7219. Min Act: -0.1700
Data Index: 4132531 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.6899. Min Act: -0.1700
Data Index: 3288640 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.6899. Min Act: -0.1700
Data Index: 7312683 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.6257. Min Act: -0.1700
Data Index: 4132528 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.6257. Min Act: -0.1699
Data Index: 4668687 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.6257. Min Act: -0.1700
Data Index: 4236813 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5936. Min Act: -0.1699
Data Index: 7885315 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5936. Min Act: -0.1700
Data Index: 5403660 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5613. Min Act: -0.1700
Data Index: 7442522 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5613. Min Act: -0.1700
Data Index: 1844489 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5613. Min Act: -0.1700
Data Index: 8011433 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5290. Min Act: -0.1700
Data Index: 1204125 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5290. Min Act: -0.1700
Data Index: 2641618 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5290. Min Act: -0.1700
Data Index: 5274446 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5290. Min Act: -0.1700
Data Index: 1734036 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0394. Min Range: -3.0394
Max Act: 2.5128. Min Act: -0.1696
Data Index: 6979803 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19