Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.9754. Min Act: -0.1700
Data Index: 2343576 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7879. Min Act: -0.1700
Data Index: 2297052 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.8191. Min Act: -0.1700
Data Index: 7572906 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7879. Min Act: -0.1700
Data Index: 1257788 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7566. Min Act: -0.1700
Data Index: 5559667 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7254. Min Act: -0.1700
Data Index: 7421853 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7254. Min Act: -0.1700
Data Index: 4840833 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7254. Min Act: -0.1700
Data Index: 1187466 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.7254. Min Act: -0.1700
Data Index: 1356423 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6941. Min Act: -0.1700
Data Index: 8151546 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6941. Min Act: -0.1700
Data Index: 5738771 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6941. Min Act: -0.1700
Data Index: 8633652 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6941. Min Act: -0.1700
Data Index: 4972726 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 1769732 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 6794807 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 1288601 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 836239 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 3566195 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 2046815 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9754. Min Range: -6.9754
Max Act: 6.6629. Min Act: -0.1700
Data Index: 3042237 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19