Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.8318. Min Act: -0.1700
Data Index: 66976 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.6754. Min Act: -0.1700
Data Index: 6988190 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.6441. Min Act: -0.1700
Data Index: 3644440 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.5972. Min Act: -0.1700
Data Index: 3795357 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.5972. Min Act: -0.1700
Data Index: 433832 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.5815. Min Act: -0.1700
Data Index: 2827824 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.5032. Min Act: -0.1700
Data Index: 4889147 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.5032. Min Act: -0.1700
Data Index: 3299272 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4876. Min Act: -0.1700
Data Index: 7595952 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4876. Min Act: -0.1700
Data Index: 8363772 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4719. Min Act: -0.1700
Data Index: 1994233 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4563. Min Act: -0.1700
Data Index: 2614504 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4719. Min Act: -0.1700
Data Index: 4572814 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4249. Min Act: -0.1700
Data Index: 5796889 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4406. Min Act: -0.1700
Data Index: 5763259 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4249. Min Act: -0.1700
Data Index: 2263290 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4092. Min Act: -0.1700
Data Index: 4798487 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.3936. Min Act: -0.1700
Data Index: 7457437 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4249. Min Act: -0.1700
Data Index: 4043358 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8318. Min Range: -3.8318
Max Act: 3.4249. Min Act: -0.1700
Data Index: 1446914 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19