Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3194 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.5126. Min Act: -0.1700
Data Index: 1763497 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.4813. Min Act: -0.1700
Data Index: 8565636 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.3876. Min Act: -0.1700
Data Index: 4921916 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2938. Min Act: -0.1700
Data Index: 3285036 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2626. Min Act: -0.1700
Data Index: 8790544 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2626. Min Act: -0.1700
Data Index: 2587303 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2313. Min Act: -0.1700
Data Index: 2137461 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2001. Min Act: -0.1700
Data Index: 1524547 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2001. Min Act: -0.1700
Data Index: 2999130 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.2001. Min Act: -0.1700
Data Index: 4892499 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.1376. Min Act: -0.1700
Data Index: 2186426 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.1688. Min Act: -0.1700
Data Index: 8605557 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.1376. Min Act: -0.1700
Data Index: 5812203 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.1063. Min Act: -0.1700
Data Index: 5818881 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0438. Min Act: -0.1700
Data Index: 235967 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0751. Min Act: -0.1700
Data Index: 8717798 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0751. Min Act: -0.1700
Data Index: 1105643 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0126. Min Act: -0.1700
Data Index: 7316627 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0438. Min Act: -0.1700
Data Index: 2252996 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5126. Min Range: -5.5126
Max Act: 5.0438. Min Act: -0.1700
Data Index: 7412505 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19