Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 612 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.3198. Min Act: -0.0000

Data Index: 51206 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.1473. Min Act: -0.0000

Data Index: 890092 (The Pile)

Max Activating Token Index: 777

Text #2

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0328. Min Act: -0.0000

Data Index: 590582 (The Pile)

Max Activating Token Index: 154

Text #3

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.2285. Min Act: -0.0000

Data Index: 222150 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0251. Min Act: -0.0000

Data Index: 115923 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.1409. Min Act: -0.0000

Data Index: 993857 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1748928 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.2414. Min Act: -0.0000

Data Index: 69567 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0754. Min Act: -0.0000

Data Index: 1034579 (The Pile)

Max Activating Token Index: 515

Text #9

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.2080. Min Act: -0.0000

Data Index: 262505 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1486021 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0211. Min Act: -0.0000

Data Index: 422135 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0272. Min Act: -0.0000

Data Index: 825444 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.1195. Min Act: -0.0000

Data Index: 423933 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9928. Min Act: -0.0000

Data Index: 998640 (The Pile)

Max Activating Token Index: 1004

Text #15

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9802. Min Act: -0.0000

Data Index: 858692 (The Pile)

Max Activating Token Index: 250

Text #16

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1051854 (The Pile)

Max Activating Token Index: 524

Text #17

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1305526 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 1.3198. Min Range: -1.3198

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1295735 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 1.3198. Min Range: -1.3198

Max Act: 0.9921. Min Act: -0.0000

Data Index: 586602 (The Pile)

Max Activating Token Index: 678