Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3693 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.5047. Min Act: -0.1700
Data Index: 4915656 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4871. Min Act: -0.1700
Data Index: 5923101 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4783. Min Act: -0.1700
Data Index: 7605286 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4519. Min Act: -0.1700
Data Index: 4808424 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4431. Min Act: -0.1700
Data Index: 8173944 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4431. Min Act: -0.1700
Data Index: 4184866 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4343. Min Act: -0.1700
Data Index: 1643605 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4431. Min Act: -0.1699
Data Index: 7742843 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4343. Min Act: -0.1699
Data Index: 7262041 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4431. Min Act: -0.1700
Data Index: 5304425 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4255. Min Act: -0.1700
Data Index: 1656348 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4255. Min Act: -0.1700
Data Index: 8748513 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4167. Min Act: -0.1700
Data Index: 1649 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4167. Min Act: -0.1700
Data Index: 6924543 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.3991. Min Act: -0.1700
Data Index: 3661314 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4079. Min Act: -0.1700
Data Index: 2929462 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.4079. Min Act: -0.1700
Data Index: 6238977 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.3991. Min Act: -0.1700
Data Index: 3841973 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.3991. Min Act: -0.1700
Data Index: 3430965 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5047. Min Range: -1.5047
Max Act: 1.3991. Min Act: -0.1700
Data Index: 3846456 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19