Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3532 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 4892850 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 4489773 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4263. Min Act: -0.1700
Data Index: 554412 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4263. Min Act: -0.1700
Data Index: 1388710 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 7256885 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.3638. Min Act: -0.1700
Data Index: 4722409 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.3638. Min Act: -0.1700
Data Index: 3380635 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.3638. Min Act: -0.1700
Data Index: 6461548 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 3993675 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 3601979 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 1831823 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 2636589 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 887105 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1763. Min Act: -0.1700
Data Index: 8402145 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1763. Min Act: -0.1700
Data Index: 3120786 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1138. Min Act: -0.1700
Data Index: 820615 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1763. Min Act: -0.1700
Data Index: 1500309 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1138. Min Act: -0.1700
Data Index: 8402144 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.1138. Min Act: -0.1700
Data Index: 2557439 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4888. Min Range: -8.4888
Max Act: 8.0513. Min Act: -0.1700
Data Index: 3632068 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19