Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.8472. Min Act: -0.1700
Data Index: 2704613 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.6126. Min Act: -0.1700
Data Index: 8248238 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.6282. Min Act: -0.1700
Data Index: 697893 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5969. Min Act: -0.1700
Data Index: 3657940 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5969. Min Act: -0.1700
Data Index: 4470396 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5813. Min Act: -0.1700
Data Index: 4105725 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5656. Min Act: -0.1700
Data Index: 429031 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5500. Min Act: -0.1700
Data Index: 8159814 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5343. Min Act: -0.1700
Data Index: 2758517 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5343. Min Act: -0.1700
Data Index: 1951345 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5343. Min Act: -0.1700
Data Index: 543190 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5187. Min Act: -0.1700
Data Index: 2858475 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5187. Min Act: -0.1700
Data Index: 7877464 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5187. Min Act: -0.1700
Data Index: 7845807 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5030. Min Act: -0.1700
Data Index: 7423498 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5030. Min Act: -0.1700
Data Index: 1902773 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.5030. Min Act: -0.1700
Data Index: 5031181 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.4873. Min Act: -0.1700
Data Index: 5464626 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.4873. Min Act: -0.1700
Data Index: 8185838 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8472. Min Range: -3.8472
Max Act: 3.4873. Min Act: -0.1700
Data Index: 3081775 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19