Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4505 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4943. Min Range: -6.4943
Max Act: 6.4943. Min Act: -0.1700
Data Index: 953574 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4943. Min Range: -6.4943
Max Act: 6.2443. Min Act: -0.1700
Data Index: 4680120 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9943. Min Act: -0.1700
Data Index: 1069516 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9943. Min Act: -0.1700
Data Index: 2821441 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9631. Min Act: -0.1700
Data Index: 8268638 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9318. Min Act: -0.1700
Data Index: 8808836 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5273278 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9631. Min Act: -0.1700
Data Index: 7437393 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9318. Min Act: -0.1700
Data Index: 5836857 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9006. Min Act: -0.1700
Data Index: 5671553 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.9006. Min Act: -0.1700
Data Index: 2480783 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8693. Min Act: -0.1700
Data Index: 6271687 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8381. Min Act: -0.1700
Data Index: 78214 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8381. Min Act: -0.1700
Data Index: 3637083 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8381. Min Act: -0.1700
Data Index: 5227687 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5191555 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8068. Min Act: -0.1700
Data Index: 8808963 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8068. Min Act: -0.1700
Data Index: 6127458 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.7756. Min Act: -0.1700
Data Index: 117600 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4943. Min Range: -6.4943
Max Act: 5.8068. Min Act: -0.1700
Data Index: 6115268 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19