Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.9025. Min Act: -0.1700
Data Index: 6896498 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8400. Min Act: -0.1700
Data Index: 6452160 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8400. Min Act: -0.1700
Data Index: 5087895 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.8243. Min Act: -0.1700
Data Index: 4048516 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7774. Min Act: -0.1700
Data Index: 2528406 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7931. Min Act: -0.1700
Data Index: 2352377 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7774. Min Act: -0.1700
Data Index: 7339909 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7618. Min Act: -0.1700
Data Index: 899224 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7774. Min Act: -0.1700
Data Index: 6402768 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7461. Min Act: -0.1700
Data Index: 5418565 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 7432334 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7461. Min Act: -0.1700
Data Index: 4998710 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7149. Min Act: -0.1700
Data Index: 1704203 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 2842976 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 7866971 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 1997494 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7149. Min Act: -0.1700
Data Index: 981367 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7305. Min Act: -0.1700
Data Index: 1749421 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7149. Min Act: -0.1700
Data Index: 7312111 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9025. Min Range: -3.9025
Max Act: 3.7149. Min Act: -0.1700
Data Index: 464150 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19