Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.3667. Min Act: -0.1700
Data Index: 4037177 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.3355. Min Act: -0.1700
Data Index: 7734636 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.3042. Min Act: -0.1700
Data Index: 3964433 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.3042. Min Act: -0.1700
Data Index: 6061249 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2417. Min Act: -0.1700
Data Index: 6708050 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2730. Min Act: -0.1700
Data Index: 3964434 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2730. Min Act: -0.1700
Data Index: 1169946 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2417. Min Act: -0.1700
Data Index: 1967023 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2105. Min Act: -0.1700
Data Index: 4001781 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2105. Min Act: -0.1700
Data Index: 18715 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2105. Min Act: -0.1700
Data Index: 6714391 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.2105. Min Act: -0.1700
Data Index: 88019 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1792. Min Act: -0.1700
Data Index: 2360857 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1792. Min Act: -0.1700
Data Index: 738163 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1792. Min Act: -0.1700
Data Index: 5719724 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1792. Min Act: -0.1700
Data Index: 8175673 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1169947 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1167. Min Act: -0.1700
Data Index: 1409994 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1167. Min Act: -0.1700
Data Index: 3984873 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3667. Min Range: -5.3667
Max Act: 5.1167. Min Act: -0.1700
Data Index: 2360858 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19