Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.7480. Min Act: -0.1700
Data Index: 600784 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.6230. Min Act: -0.1700
Data Index: 606648 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.5605. Min Act: -0.1700
Data Index: 1961719 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.4355. Min Act: -0.1700
Data Index: 3371476 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.4355. Min Act: -0.1700
Data Index: 5870860 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.4042. Min Act: -0.1700
Data Index: 3998288 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3730. Min Act: -0.1700
Data Index: 1550229 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3730. Min Act: -0.1700
Data Index: 7392379 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3417. Min Act: -0.1700
Data Index: 5725669 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3417. Min Act: -0.1700
Data Index: 3929477 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 5080373 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 5222127 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 1545784 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 4155529 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 4729760 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 2312549 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 838371 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 3092718 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.2792. Min Act: -0.1700
Data Index: 2474259 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7480. Min Range: -4.7480
Max Act: 4.3105. Min Act: -0.1700
Data Index: 7704698 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19