Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2869 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5478. Min Range: -9.5478
Max Act: 9.5478. Min Act: -0.1700
Data Index: 4480958 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5478. Min Range: -9.5478
Max Act: 9.1103. Min Act: -0.1700
Data Index: 2199086 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.9853. Min Act: -0.1700
Data Index: 2837013 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.9228. Min Act: -0.1700
Data Index: 7547006 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.9228. Min Act: -0.1700
Data Index: 6390354 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.8603. Min Act: -0.1700
Data Index: 7121266 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.7978. Min Act: -0.1700
Data Index: 6448900 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.7978. Min Act: -0.1700
Data Index: 1625624 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.7978. Min Act: -0.1700
Data Index: 4659429 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.7353. Min Act: -0.1700
Data Index: 347611 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.7353. Min Act: -0.1700
Data Index: 929654 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.6728. Min Act: -0.1700
Data Index: 8541037 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.6728. Min Act: -0.1700
Data Index: 717194 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.6103. Min Act: -0.1700
Data Index: 8797296 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.5478. Min Act: -0.1700
Data Index: 2713807 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.5478. Min Act: -0.1700
Data Index: 1237913 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.5478. Min Act: -0.1700
Data Index: 6663659 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.5478. Min Act: -0.1700
Data Index: 3098587 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.4853. Min Act: -0.1700
Data Index: 3450503 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5478. Min Range: -9.5478
Max Act: 8.4853. Min Act: -0.1700
Data Index: 2256435 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19