Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3370 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.9448. Min Act: -0.1700
Data Index: 1695012 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.8353. Min Act: -0.1700
Data Index: 3195178 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.8353. Min Act: -0.1700
Data Index: 7305474 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.7259. Min Act: -0.1700
Data Index: 4034950 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.7102. Min Act: -0.1700
Data Index: 3873274 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.7102. Min Act: -0.1700
Data Index: 1355177 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6946. Min Act: -0.1700
Data Index: 5962714 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6476. Min Act: -0.1700
Data Index: 3370893 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6476. Min Act: -0.1700
Data Index: 6647905 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6163. Min Act: -0.1700
Data Index: 2715702 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6476. Min Act: -0.1700
Data Index: 1904073 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6320. Min Act: -0.1700
Data Index: 4882153 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6163. Min Act: -0.1700
Data Index: 5677272 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6163. Min Act: -0.1700
Data Index: 6728313 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6320. Min Act: -0.1700
Data Index: 6909189 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6163. Min Act: -0.1700
Data Index: 6033830 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6007. Min Act: -0.1700
Data Index: 4049642 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6163. Min Act: -0.1700
Data Index: 6336529 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.6007. Min Act: -0.1700
Data Index: 4472616 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9448. Min Range: -3.9448
Max Act: 3.5694. Min Act: -0.1700
Data Index: 7035110 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19