Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.2676. Min Act: -0.1700
Data Index: 5283170 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.2363. Min Act: -0.1700
Data Index: 95939 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.1426. Min Act: -0.1700
Data Index: 2338960 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.1738. Min Act: -0.1700
Data Index: 5995126 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.1426. Min Act: -0.1700
Data Index: 1513228 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.1426. Min Act: -0.1700
Data Index: 3779958 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.1426. Min Act: -0.1700
Data Index: 872572 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0801. Min Act: -0.1700
Data Index: 3349216 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0488. Min Act: -0.1700
Data Index: 6308284 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0801. Min Act: -0.1700
Data Index: 4329735 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0801. Min Act: -0.1700
Data Index: 663192 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0488. Min Act: -0.1700
Data Index: 6017704 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0488. Min Act: -0.1700
Data Index: 8092324 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4773096 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0176. Min Act: -0.1700
Data Index: 6255233 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4089839 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2676. Min Range: -5.2676
Max Act: 5.0176. Min Act: -0.1700
Data Index: 2582329 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2676. Min Range: -5.2676
Max Act: 4.9863. Min Act: -0.1700
Data Index: 3977670 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2676. Min Range: -5.2676
Max Act: 4.9863. Min Act: -0.1700
Data Index: 1349666 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2676. Min Range: -5.2676
Max Act: 4.9863. Min Act: -0.1700
Data Index: 2242037 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19