Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 399 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.9882. Min Act: -0.1700
Data Index: 1643364 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.8007. Min Act: -0.1700
Data Index: 2567972 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.8007. Min Act: -0.1700
Data Index: 4590867 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.8007. Min Act: -0.1700
Data Index: 1690807 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7382. Min Act: -0.1700
Data Index: 1051251 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7382. Min Act: -0.1700
Data Index: 4468844 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.7382. Min Act: -0.1700
Data Index: 7342080 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6757. Min Act: -0.1700
Data Index: 8731490 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6132. Min Act: -0.1700
Data Index: 1032264 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6132. Min Act: -0.1700
Data Index: 804917 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 6184973 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 1815120 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 7255024 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 2826597 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 6144311 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.6132. Min Act: -0.1700
Data Index: 8500201 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 6829394 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.5507. Min Act: -0.1700
Data Index: 6859920 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 4240273 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9882. Min Range: -7.9882
Max Act: 7.4882. Min Act: -0.1700
Data Index: 3201888 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19