Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1010 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1754. Min Range: -10.1754
Max Act: 10.1754. Min Act: -0.1700
Data Index: 5702279 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1754. Min Range: -10.1754
Max Act: 9.8004. Min Act: -0.1700
Data Index: 4133024 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1754. Min Range: -10.1754
Max Act: 9.4879. Min Act: -0.1700
Data Index: 1131023 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1754. Min Range: -10.1754
Max Act: 9.1754. Min Act: -0.1700
Data Index: 5044924 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1754. Min Range: -10.1754
Max Act: 9.1754. Min Act: -0.1700
Data Index: 2762859 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1754. Min Range: -10.1754
Max Act: 9.0504. Min Act: -0.1700
Data Index: 7088705 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.8629. Min Act: -0.1700
Data Index: 8643501 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.8004. Min Act: -0.1700
Data Index: 2863613 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.8004. Min Act: -0.1700
Data Index: 4542415 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.7379. Min Act: -0.1700
Data Index: 7458013 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.8004. Min Act: -0.1700
Data Index: 6023402 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.8004. Min Act: -0.1700
Data Index: 3848600 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.7379. Min Act: -0.1700
Data Index: 7786357 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6754. Min Act: -0.1700
Data Index: 7605997 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6129. Min Act: -0.1700
Data Index: 3385621 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6129. Min Act: -0.1700
Data Index: 5807860 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6129. Min Act: -0.1700
Data Index: 1394796 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6754. Min Act: -0.1700
Data Index: 5800171 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6129. Min Act: -0.1700
Data Index: 2388562 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1754. Min Range: -10.1754
Max Act: 8.6129. Min Act: -0.1700
Data Index: 8258001 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19