Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5970 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.4382. Min Act: -0.1700
Data Index: 7575038 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.4056. Min Act: -0.1700
Data Index: 3528459 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.4056. Min Act: -0.1700
Data Index: 5215638 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.4056. Min Act: -0.1700
Data Index: 7342902 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3893. Min Act: -0.1700
Data Index: 2107999 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3566. Min Act: -0.1700
Data Index: 18330 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3402. Min Act: -0.1700
Data Index: 4415401 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3402. Min Act: -0.1700
Data Index: 7290000 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3402. Min Act: -0.1700
Data Index: 7308695 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3238. Min Act: -0.1700
Data Index: 5619556 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3238. Min Act: -0.1700
Data Index: 1013399 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3402. Min Act: -0.1700
Data Index: 7111587 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3238. Min Act: -0.1700
Data Index: 7032002 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3238. Min Act: -0.1700
Data Index: 232304 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3074. Min Act: -0.1700
Data Index: 6573085 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3074. Min Act: -0.1700
Data Index: 7374115 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.2909. Min Act: -0.1700
Data Index: 4052253 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3074. Min Act: -0.1700
Data Index: 3058071 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3074. Min Act: -0.1700
Data Index: 8376954 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4382. Min Range: -2.4382
Max Act: 2.3074. Min Act: -0.1700
Data Index: 8633816 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #19