Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4853. Min Range: -7.4853
Max Act: 7.4853. Min Act: -0.1700
Data Index: 1382770 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4853. Min Range: -7.4853
Max Act: 7.4228. Min Act: -0.1700
Data Index: 4224600 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4853. Min Range: -7.4853
Max Act: 7.3603. Min Act: -0.1700
Data Index: 3358294 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4853. Min Range: -7.4853
Max Act: 7.3290. Min Act: -0.1700
Data Index: 788528 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4853. Min Range: -7.4853
Max Act: 7.2353. Min Act: -0.1700
Data Index: 7487387 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.9228. Min Act: -0.1700
Data Index: 102612 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.9228. Min Act: -0.1700
Data Index: 699385 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.8603. Min Act: -0.1700
Data Index: 7446269 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.8603. Min Act: -0.1700
Data Index: 1362272 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.8290. Min Act: -0.1700
Data Index: 3086928 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.8290. Min Act: -0.1700
Data Index: 6963795 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.8290. Min Act: -0.1700
Data Index: 1616177 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 8341129 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 4731172 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 5986537 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 4197919 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 5698014 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7665. Min Act: -0.1700
Data Index: 820560 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7353. Min Act: -0.1700
Data Index: 2318038 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4853. Min Range: -7.4853
Max Act: 6.7353. Min Act: -0.1700
Data Index: 2481019 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19