Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.6637. Min Act: -0.1700
Data Index: 5606507 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.5075. Min Act: -0.1700
Data Index: 4053241 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.4450. Min Act: -0.1700
Data Index: 2673553 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.4762. Min Act: -0.1700
Data Index: 1771850 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.4450. Min Act: -0.1700
Data Index: 5558261 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3825. Min Act: -0.1700
Data Index: 2988308 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3603150 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3928449 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3825. Min Act: -0.1700
Data Index: 3965024 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3512. Min Act: -0.1700
Data Index: 2780099 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3512. Min Act: -0.1700
Data Index: 8197332 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3512. Min Act: -0.1700
Data Index: 7882804 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7648214 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3512. Min Act: -0.1700
Data Index: 6330178 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3512. Min Act: -0.1700
Data Index: 8729837 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7451551 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3200. Min Act: -0.1700
Data Index: 4080120 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3200. Min Act: -0.1700
Data Index: 30982 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.3200. Min Act: -0.1700
Data Index: 5535211 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6637. Min Range: -4.6637
Max Act: 4.2887. Min Act: -0.1700
Data Index: 3908655 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19