Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3782 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.9458. Min Act: -0.1700
Data Index: 4778147 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.7583. Min Act: -0.1700
Data Index: 312475 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.7270. Min Act: -0.1700
Data Index: 6627395 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.6645. Min Act: -0.1700
Data Index: 2214930 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.5708. Min Act: -0.1700
Data Index: 5339109 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4770. Min Act: -0.1700
Data Index: 2644459 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4770. Min Act: -0.1700
Data Index: 5548866 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4770. Min Act: -0.1700
Data Index: 2269374 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4145. Min Act: -0.1700
Data Index: 37666 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4458. Min Act: -0.1700
Data Index: 835737 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.4145. Min Act: -0.1700
Data Index: 3758755 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.3208. Min Act: -0.1700
Data Index: 7606952 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.2895. Min Act: -0.1700
Data Index: 4742743 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.2270. Min Act: -0.1700
Data Index: 4489068 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.2270. Min Act: -0.1700
Data Index: 7704470 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.1958. Min Act: -0.1700
Data Index: 5340087 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.2270. Min Act: -0.1700
Data Index: 1762922 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.2270. Min Act: -0.1700
Data Index: 2512350 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.1958. Min Act: -0.1700
Data Index: 32046 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9458. Min Range: -7.9458
Max Act: 7.1958. Min Act: -0.1700
Data Index: 6227777 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19