Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.8421. Min Act: -0.1700
Data Index: 4843457 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.8421. Min Act: -0.1700
Data Index: 2065599 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.7796. Min Act: -0.1700
Data Index: 58468 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.6859. Min Act: -0.1700
Data Index: 5842306 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.6546. Min Act: -0.1700
Data Index: 71914 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.6234. Min Act: -0.1700
Data Index: 5336483 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.6234. Min Act: -0.1700
Data Index: 2887765 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5921. Min Act: -0.1700
Data Index: 1077936 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5609. Min Act: -0.1700
Data Index: 2533056 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5921. Min Act: -0.1700
Data Index: 2147689 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5921. Min Act: -0.1700
Data Index: 596294 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5609. Min Act: -0.1700
Data Index: 4367740 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5609. Min Act: -0.1700
Data Index: 2452502 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5609. Min Act: -0.1700
Data Index: 697291 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5609. Min Act: -0.1700
Data Index: 5136345 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.4984. Min Act: -0.1700
Data Index: 5195776 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5296. Min Act: -0.1700
Data Index: 6270047 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5296. Min Act: -0.1700
Data Index: 5563269 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.4984. Min Act: -0.1700
Data Index: 2771263 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8421. Min Range: -4.8421
Max Act: 4.5296. Min Act: -0.1700
Data Index: 758867 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19