Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2595 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.3967. Min Act: -0.1700
Data Index: 8654451 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.2092. Min Act: -0.1700
Data Index: 6506662 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.2092. Min Act: -0.1700
Data Index: 2657439 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1780. Min Act: -0.1700
Data Index: 5007318 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1467. Min Act: -0.1700
Data Index: 8465496 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 5796340 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 5884445 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 2644127 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 580821 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 7303952 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.1155. Min Act: -0.1700
Data Index: 4931266 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0842. Min Act: -0.1700
Data Index: 3198161 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0842. Min Act: -0.1700
Data Index: 7563407 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0842. Min Act: -0.1698
Data Index: 476730 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0530. Min Act: -0.1700
Data Index: 6064799 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0530. Min Act: -0.1700
Data Index: 2757855 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0530. Min Act: -0.1700
Data Index: 7827584 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0530. Min Act: -0.1700
Data Index: 4497037 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0217. Min Act: -0.1700
Data Index: 5131349 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3967. Min Range: -6.3967
Max Act: 6.0530. Min Act: -0.1700
Data Index: 3017574 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19