Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2557. Min Range: -4.2557
Max Act: 4.2557. Min Act: -0.1700
Data Index: 1581675 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2557. Min Range: -4.2557
Max Act: 4.0994. Min Act: -0.1700
Data Index: 4998835 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2557. Min Range: -4.2557
Max Act: 4.0682. Min Act: -0.1700
Data Index: 1767555 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2557. Min Range: -4.2557
Max Act: 4.0369. Min Act: -0.1700
Data Index: 1042145 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.9431. Min Act: -0.1700
Data Index: 1034976 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.8806. Min Act: -0.1700
Data Index: 824822 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.8181. Min Act: -0.1700
Data Index: 8395682 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.8181. Min Act: -0.1700
Data Index: 290835 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.8181. Min Act: -0.1700
Data Index: 3352786 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7555. Min Act: -0.1700
Data Index: 4958229 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7868. Min Act: -0.1700
Data Index: 356837 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7555. Min Act: -0.1700
Data Index: 4358031 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7555. Min Act: -0.1700
Data Index: 4444179 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7555. Min Act: -0.1700
Data Index: 8648842 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7399. Min Act: -0.1700
Data Index: 5676961 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7399. Min Act: -0.1700
Data Index: 5175065 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7086. Min Act: -0.1700
Data Index: 5318737 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.6930. Min Act: -0.1700
Data Index: 2250797 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7086. Min Act: -0.1700
Data Index: 7681485 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2557. Min Range: -4.2557
Max Act: 3.7086. Min Act: -0.1700
Data Index: 559188 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19