Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 709 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.9611. Min Act: -0.1700
Data Index: 1151031 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.8986. Min Act: -0.1700
Data Index: 441881 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7736. Min Act: -0.1700
Data Index: 1795429 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7736. Min Act: -0.1700
Data Index: 453218 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.8048. Min Act: -0.1700
Data Index: 3522462 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2765540 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7111. Min Act: -0.1700
Data Index: 3380273 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7111. Min Act: -0.1700
Data Index: 5106313 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2478131 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7111. Min Act: -0.1700
Data Index: 5870389 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.7423. Min Act: -0.1700
Data Index: 490224 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6798. Min Act: -0.1700
Data Index: 6760020 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6798. Min Act: -0.1700
Data Index: 794421 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6798. Min Act: -0.1700
Data Index: 1262760 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6798. Min Act: -0.1700
Data Index: 1657472 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6798. Min Act: -0.1700
Data Index: 4206256 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6486. Min Act: -0.1700
Data Index: 2017148 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6486. Min Act: -0.1700
Data Index: 2081278 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6486. Min Act: -0.1700
Data Index: 3378028 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9611. Min Range: -5.9611
Max Act: 5.6486. Min Act: -0.1700
Data Index: 7991479 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19