Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5917 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9445. Min Act: -0.1700
Data Index: 7419608 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.9128. Min Act: -0.1700
Data Index: 4874733 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8810. Min Act: -0.1700
Data Index: 3708784 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 7049227 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8810. Min Act: -0.1700
Data Index: 7628998 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 2702453 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 7420839 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8334. Min Act: -0.1700
Data Index: 572990 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8493. Min Act: -0.1700
Data Index: 7049220 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8652. Min Act: -0.1700
Data Index: 6076713 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 7393167 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8334. Min Act: -0.1700
Data Index: 2115816 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8334. Min Act: -0.1700
Data Index: 7628997 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8493. Min Act: -0.1700
Data Index: 8531369 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8493. Min Act: -0.1700
Data Index: 2662087 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 3396124 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 4752421 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 2582684 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8175. Min Act: -0.1700
Data Index: 1275144 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9445. Min Range: -2.9445
Max Act: 2.8016. Min Act: -0.1700
Data Index: 6139745 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19