Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4680 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.7131. Min Act: -0.1700
Data Index: 3929130 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.6819. Min Act: -0.1700
Data Index: 1643187 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.5569. Min Act: -0.1700
Data Index: 603127 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.4006. Min Act: -0.1700
Data Index: 7183074 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.4006. Min Act: -0.1700
Data Index: 5026962 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6442336 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6069377 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3381. Min Act: -0.1700
Data Index: 1099783 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3381. Min Act: -0.1700
Data Index: 6786608 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3381. Min Act: -0.1700
Data Index: 7793115 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.3381. Min Act: -0.1700
Data Index: 7420369 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2756. Min Act: -0.1700
Data Index: 3596429 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2756. Min Act: -0.1700
Data Index: 417391 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2444. Min Act: -0.1700
Data Index: 4388664 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2444. Min Act: -0.1700
Data Index: 6589335 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2444. Min Act: -0.1700
Data Index: 7821419 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2756. Min Act: -0.1700
Data Index: 3754245 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2131. Min Act: -0.1700
Data Index: 4828370 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.2131. Min Act: -0.1700
Data Index: 805095 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7131. Min Range: -5.7131
Max Act: 5.1819. Min Act: -0.1700
Data Index: 6344038 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19