Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3966. Min Range: -4.3966
Max Act: 4.3966. Min Act: -0.1700
Data Index: 675465 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3966. Min Range: -4.3966
Max Act: 4.1154. Min Act: -0.1700
Data Index: 931592 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.9903. Min Act: -0.1700
Data Index: 665471 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.9903. Min Act: -0.1700
Data Index: 7726358 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.9591. Min Act: -0.1700
Data Index: 7342599 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.9278. Min Act: -0.1700
Data Index: 6430566 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8965. Min Act: -0.1700
Data Index: 2276423 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8965. Min Act: -0.1700
Data Index: 1971951 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5044672 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8965. Min Act: -0.1700
Data Index: 5562865 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8653. Min Act: -0.1700
Data Index: 3439729 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 5365383 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 8001271 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 6151830 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 1006628 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 1702512 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 8005725 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8340. Min Act: -0.1700
Data Index: 8731427 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8027. Min Act: -0.1700
Data Index: 2797171 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3966. Min Range: -4.3966
Max Act: 3.8027. Min Act: -0.1700
Data Index: 300498 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19