Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3891 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2189. Min Range: -7.2189
Max Act: 7.2189. Min Act: -0.1700
Data Index: 2066464 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.9376. Min Act: -0.1700
Data Index: 3751311 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.9064. Min Act: -0.1700
Data Index: 708279 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.8751. Min Act: -0.1700
Data Index: 6046503 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.8439. Min Act: -0.1700
Data Index: 913424 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.8126. Min Act: -0.1700
Data Index: 5591954 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.7189. Min Act: -0.1700
Data Index: 2760048 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6876. Min Act: -0.1700
Data Index: 1303635 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6564. Min Act: -0.1700
Data Index: 3301525 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6564. Min Act: -0.1700
Data Index: 576424 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6564. Min Act: -0.1700
Data Index: 2923977 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6251. Min Act: -0.1700
Data Index: 5416375 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6251. Min Act: -0.1700
Data Index: 6003966 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6251. Min Act: -0.1700
Data Index: 1314605 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.6251. Min Act: -0.1700
Data Index: 7609846 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.5626. Min Act: -0.1700
Data Index: 8144232 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.5626. Min Act: -0.1700
Data Index: 5236397 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.5626. Min Act: -0.1700
Data Index: 4345033 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.5314. Min Act: -0.1700
Data Index: 988679 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2189. Min Range: -7.2189
Max Act: 6.5001. Min Act: -0.1700
Data Index: 5798531 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19