Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0915. Min Range: -3.0915
Max Act: 3.0915. Min Act: -0.1700
Data Index: 5916746 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0915. Min Range: -3.0915
Max Act: 3.0758. Min Act: -0.1700
Data Index: 2657369 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.9494. Min Act: -0.1700
Data Index: 8000042 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.8383. Min Act: -0.1700
Data Index: 185085 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.8224. Min Act: -0.1700
Data Index: 8570801 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7906. Min Act: -0.1700
Data Index: 6302608 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7747. Min Act: -0.1700
Data Index: 2459372 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7587. Min Act: -0.1700
Data Index: 4233864 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7747. Min Act: -0.1700
Data Index: 8782476 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7587. Min Act: -0.1700
Data Index: 932304 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.8224. Min Act: -0.1700
Data Index: 1344631 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7427. Min Act: -0.1700
Data Index: 5847636 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7108. Min Act: -0.1700
Data Index: 7399094 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7427. Min Act: -0.1700
Data Index: 1767256 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7108. Min Act: -0.1700
Data Index: 6310375 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7587. Min Act: -0.1700
Data Index: 3035356 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7268. Min Act: -0.1700
Data Index: 7143766 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7268. Min Act: -0.1700
Data Index: 2301522 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7587. Min Act: -0.1700
Data Index: 5706342 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0915. Min Range: -3.0915
Max Act: 2.7108. Min Act: -0.1700
Data Index: 5283725 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19