Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 32 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1609423 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1233633 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4610. Min Act: -0.1700
Data Index: 4764681 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1325721 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4610. Min Act: -0.1700
Data Index: 4833279 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4297. Min Act: -0.1700
Data Index: 7094601 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.4297. Min Act: -0.1700
Data Index: 6680341 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3985. Min Act: -0.1700
Data Index: 788959 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3672. Min Act: -0.1700
Data Index: 5897411 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3360. Min Act: -0.1700
Data Index: 5295237 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3360. Min Act: -0.1700
Data Index: 1492470 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3047. Min Act: -0.1700
Data Index: 6819633 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3360. Min Act: -0.1700
Data Index: 450060 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3047. Min Act: -0.1700
Data Index: 4828339 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3047. Min Act: -0.1700
Data Index: 6852659 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.3047. Min Act: -0.1700
Data Index: 5421607 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.2735. Min Act: -0.1700
Data Index: 2736403 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.2735. Min Act: -0.1700
Data Index: 484791 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.2735. Min Act: -0.1700
Data Index: 3050817 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4610. Min Range: -4.4610
Max Act: 4.2735. Min Act: -0.1700
Data Index: 2736404 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19