Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2316. Min Range: -7.2316
Max Act: 7.2316. Min Act: -0.1700
Data Index: 4953223 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.9816. Min Act: -0.1700
Data Index: 6836376 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.8566. Min Act: -0.1700
Data Index: 1254502 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.6379. Min Act: -0.1700
Data Index: 7725953 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.6379. Min Act: -0.1700
Data Index: 5204380 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.5441. Min Act: -0.1700
Data Index: 3867265 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.4504. Min Act: -0.1700
Data Index: 3616706 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.3566. Min Act: -0.1700
Data Index: 2758587 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.3566. Min Act: -0.1700
Data Index: 2555143 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.3254. Min Act: -0.1700
Data Index: 4692855 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.3254. Min Act: -0.1700
Data Index: 3947072 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2941. Min Act: -0.1700
Data Index: 2587549 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2941. Min Act: -0.1700
Data Index: 1517457 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2941. Min Act: -0.1700
Data Index: 8049485 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2316. Min Act: -0.1700
Data Index: 4772132 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2629. Min Act: -0.1700
Data Index: 4917119 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2316. Min Act: -0.1700
Data Index: 1713129 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2629. Min Act: -0.1700
Data Index: 4312507 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2004. Min Act: -0.1700
Data Index: 3968373 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2316. Min Range: -7.2316
Max Act: 6.2004. Min Act: -0.1700
Data Index: 6773811 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19