Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8689. Min Act: -0.1700
Data Index: 4974645 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8377. Min Act: -0.1700
Data Index: 2858871 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8377. Min Act: -0.1700
Data Index: 2368873 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8377. Min Act: -0.1700
Data Index: 3736099 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8064. Min Act: -0.1700
Data Index: 7311022 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8064. Min Act: -0.1700
Data Index: 4028285 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.8064. Min Act: -0.1700
Data Index: 7325999 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7752. Min Act: -0.1700
Data Index: 661863 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7439. Min Act: -0.1700
Data Index: 4190158 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7439. Min Act: -0.1700
Data Index: 1126286 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7439. Min Act: -0.1700
Data Index: 3390689 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7127. Min Act: -0.1700
Data Index: 6907383 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7127. Min Act: -0.1700
Data Index: 2748853 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7127. Min Act: -0.1700
Data Index: 4384974 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.7127. Min Act: -0.1700
Data Index: 1051756 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.6814. Min Act: -0.1700
Data Index: 574647 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.6502. Min Act: -0.1700
Data Index: 8039061 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.6502. Min Act: -0.1700
Data Index: 2521931 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.6502. Min Act: -0.1700
Data Index: 8457517 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8689. Min Range: -4.8689
Max Act: 4.6502. Min Act: -0.1700
Data Index: 6755577 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19