Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 823 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.9840. Min Act: -0.1700
Data Index: 2368467 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.7025. Min Act: -0.1700
Data Index: 7791544 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.6399. Min Act: -0.1700
Data Index: 6409657 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.6399. Min Act: -0.1700
Data Index: 2413053 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.5930. Min Act: -0.1700
Data Index: 8423651 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.5617. Min Act: -0.1700
Data Index: 946528 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.5147. Min Act: -0.1700
Data Index: 8560556 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 5165116 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 1066637 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 839906 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 3006626 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 2182507 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4521. Min Act: -0.1700
Data Index: 4830610 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4521. Min Act: -0.1700
Data Index: 8099730 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4834. Min Act: -0.1700
Data Index: 449365 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4677. Min Act: -0.1700
Data Index: 6578679 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4521. Min Act: -0.1700
Data Index: 8389486 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4677. Min Act: -0.1700
Data Index: 6734392 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4521. Min Act: -0.1700
Data Index: 4486667 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9840. Min Range: -3.9840
Max Act: 3.4364. Min Act: -0.1700
Data Index: 3402479 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19