Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1725 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.5393. Min Act: -0.1700
Data Index: 3223854 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.3518. Min Act: -0.1700
Data Index: 4239983 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.3518. Min Act: -0.1700
Data Index: 6748884 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.3518. Min Act: -0.1700
Data Index: 8378425 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.3206. Min Act: -0.1700
Data Index: 4957707 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2893. Min Act: -0.1700
Data Index: 6458145 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2581. Min Act: -0.1700
Data Index: 2463457 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2268. Min Act: -0.1700
Data Index: 8517609 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.2268. Min Act: -0.1700
Data Index: 7867037 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1956. Min Act: -0.1700
Data Index: 6133481 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1956. Min Act: -0.1700
Data Index: 2033348 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1956. Min Act: -0.1700
Data Index: 4940690 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1956. Min Act: -0.1700
Data Index: 2228999 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 8526245 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 8632322 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 6892696 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 4975782 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1331. Min Act: -0.1700
Data Index: 5970474 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1643. Min Act: -0.1700
Data Index: 5064586 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5393. Min Range: -6.5393
Max Act: 6.1331. Min Act: -0.1700
Data Index: 8120665 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19