Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 558 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6811. Min Range: -9.6811
Max Act: 9.6811. Min Act: -0.1700
Data Index: 622791 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.9936. Min Act: -0.1700
Data Index: 6517851 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.9936. Min Act: -0.1700
Data Index: 3188612 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6811. Min Range: -9.6811
Max Act: 9.0561. Min Act: -0.1700
Data Index: 4385787 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.8061. Min Act: -0.1700
Data Index: 3858296 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.8061. Min Act: -0.1700
Data Index: 241219 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.7436. Min Act: -0.1700
Data Index: 6847204 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 4188296 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 1115431 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.5561. Min Act: -0.1700
Data Index: 7770622 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.4936. Min Act: -0.1700
Data Index: 2862168 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 6650092 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 2443774 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.4311. Min Act: -0.1700
Data Index: 3510369 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3686. Min Act: -0.1700
Data Index: 3533847 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3686. Min Act: -0.1700
Data Index: 3692565 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3686. Min Act: -0.1700
Data Index: 7064860 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3061. Min Act: -0.1700
Data Index: 2195222 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3686. Min Act: -0.1700
Data Index: 5008858 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6811. Min Range: -9.6811
Max Act: 8.3061. Min Act: -0.1700
Data Index: 1105922 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19