Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9852. Min Act: -0.1700
Data Index: 7360017 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0011. Min Range: -3.0011
Max Act: 3.0011. Min Act: -0.1700
Data Index: 2375291 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9852. Min Act: -0.1700
Data Index: 4108818 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9536. Min Act: -0.1700
Data Index: 183773 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9536. Min Act: -0.1700
Data Index: 1629122 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9378. Min Act: -0.1700
Data Index: 3018657 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9219. Min Act: -0.1700
Data Index: 2966000 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9061. Min Act: -0.1700
Data Index: 4559734 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9061. Min Act: -0.1700
Data Index: 8624257 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9061. Min Act: -0.1700
Data Index: 6200204 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9219. Min Act: -0.1700
Data Index: 6017848 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8902. Min Act: -0.1700
Data Index: 5317680 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.9061. Min Act: -0.1700
Data Index: 7617184 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8744. Min Act: -0.1700
Data Index: 8214824 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8902. Min Act: -0.1700
Data Index: 8441908 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8902. Min Act: -0.1700
Data Index: 8816834 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8744. Min Act: -0.1700
Data Index: 8437770 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8744. Min Act: -0.1700
Data Index: 3005045 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8585. Min Act: -0.1700
Data Index: 2330739 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0011. Min Range: -3.0011
Max Act: 2.8744. Min Act: -0.1700
Data Index: 6620113 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19