Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2592 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8454. Min Range: -6.8454
Max Act: 6.8454. Min Act: -0.1700
Data Index: 2370921 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8454. Min Range: -6.8454
Max Act: 6.1579. Min Act: -0.1700
Data Index: 1005347 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8454. Min Range: -6.8454
Max Act: 6.0329. Min Act: -0.1700
Data Index: 5161507 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8454. Min Range: -6.8454
Max Act: 6.0329. Min Act: -0.1700
Data Index: 7125631 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5171966 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.9391. Min Act: -0.1700
Data Index: 6404142 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.9079. Min Act: -0.1700
Data Index: 15607 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.8141. Min Act: -0.1700
Data Index: 5803701 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.8454. Min Act: -0.1700
Data Index: 6457426 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7829. Min Act: -0.1700
Data Index: 4077868 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7516. Min Act: -0.1700
Data Index: 2016070 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7516. Min Act: -0.1700
Data Index: 1451208 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7516. Min Act: -0.1700
Data Index: 8036974 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 5712232 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 4641547 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.6891. Min Act: -0.1700
Data Index: 2879173 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.6891. Min Act: -0.1700
Data Index: 7754806 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.6891. Min Act: -0.1700
Data Index: 5497736 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.7204. Min Act: -0.1700
Data Index: 204449 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8454. Min Range: -6.8454
Max Act: 5.6579. Min Act: -0.1700
Data Index: 6462639 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19