Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.3090. Min Act: -0.1700
Data Index: 1599641 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.2776. Min Act: -0.1700
Data Index: 7398995 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.2619. Min Act: -0.1700
Data Index: 8183893 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.1518. Min Act: -0.1700
Data Index: 3203387 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.1203. Min Act: -0.1700
Data Index: 7945495 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.1360. Min Act: -0.1700
Data Index: 1610429 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.1203. Min Act: -0.1700
Data Index: 2042497 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0888. Min Act: -0.1700
Data Index: 4426218 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0888. Min Act: -0.1700
Data Index: 8398214 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0730. Min Act: -0.1700
Data Index: 3529535 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0730. Min Act: -0.1700
Data Index: 6842506 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0730. Min Act: -0.1700
Data Index: 7036886 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0415. Min Act: -0.1700
Data Index: 2674103 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0572. Min Act: -0.1700
Data Index: 8316062 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0415. Min Act: -0.1700
Data Index: 4904877 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0415. Min Act: -0.1700
Data Index: 1606328 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0415. Min Act: -0.1700
Data Index: 5070279 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0257. Min Act: -0.1700
Data Index: 6391493 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0572. Min Act: -0.1700
Data Index: 592581 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3090. Min Range: -3.3090
Max Act: 3.0415. Min Act: -0.1700
Data Index: 573766 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19