Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4261 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.5929. Min Act: -0.1700
Data Index: 15972 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.5304. Min Act: -0.1700
Data Index: 8245976 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.4679. Min Act: -0.1700
Data Index: 4214388 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.4366. Min Act: -0.1700
Data Index: 8448694 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.4366. Min Act: -0.1700
Data Index: 6007473 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.2804. Min Act: -0.1700
Data Index: 2722296 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.2804. Min Act: -0.1700
Data Index: 4879938 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.2491. Min Act: -0.1700
Data Index: 7460955 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.2179. Min Act: -0.1700
Data Index: 6568879 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1866. Min Act: -0.1700
Data Index: 6587649 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1866. Min Act: -0.1700
Data Index: 5790001 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1554. Min Act: -0.1700
Data Index: 3653469 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1241. Min Act: -0.1700
Data Index: 5514163 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1241. Min Act: -0.1700
Data Index: 6682481 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.1241. Min Act: -0.1700
Data Index: 3029161 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.0929. Min Act: -0.1700
Data Index: 4334049 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.0304. Min Act: -0.1700
Data Index: 5349386 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.0304. Min Act: -0.1700
Data Index: 8194697 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5929. Min Range: -6.5929
Max Act: 6.0304. Min Act: -0.1700
Data Index: 340172 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5929. Min Range: -6.5929
Max Act: 5.9991. Min Act: -0.1700
Data Index: 1531762 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19