Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.5715. Min Act: -0.1700
Data Index: 4788360 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.5402. Min Act: -0.1700
Data Index: 7413670 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.4619. Min Act: -0.1700
Data Index: 8492747 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.4619. Min Act: -0.1700
Data Index: 5743565 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.4463. Min Act: -0.1700
Data Index: 5767055 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.4306. Min Act: -0.1700
Data Index: 5519869 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3992. Min Act: -0.1700
Data Index: 2926357 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3992. Min Act: -0.1700
Data Index: 852360 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3836. Min Act: -0.1700
Data Index: 4179791 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3836. Min Act: -0.1700
Data Index: 2035351 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3836. Min Act: -0.1700
Data Index: 8479898 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3679. Min Act: -0.1700
Data Index: 4437367 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3679. Min Act: -0.1700
Data Index: 2606998 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3522. Min Act: -0.1700
Data Index: 1980824 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3522. Min Act: -0.1700
Data Index: 6956460 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3208. Min Act: -0.1700
Data Index: 2742552 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3365. Min Act: -0.1700
Data Index: 7726640 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3522. Min Act: -0.1700
Data Index: 4532874 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3365. Min Act: -0.1700
Data Index: 2933283 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5715. Min Range: -3.5715
Max Act: 3.3208. Min Act: -0.1700
Data Index: 2391882 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19