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

Dataset: The Pile

Neuron 1137 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2609. Min Range: -1.2609

Max Act: 1.2609. Min Act: -0.0000

Data Index: 355252 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 1.2609. Min Range: -1.2609

Max Act: 1.0683. Min Act: -0.0000

Data Index: 857720 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 1.2609. Min Range: -1.2609

Max Act: 1.0265. Min Act: -0.0000

Data Index: 918175 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.2609. Min Range: -1.2609

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1647698 (The Pile)

Max Activating Token Index: 376

Text #4

Max Range: 1.2609. Min Range: -1.2609

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1157363 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1600582 (The Pile)

Max Activating Token Index: 113

Text #6

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1207895 (The Pile)

Max Activating Token Index: 206

Text #7

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1649167 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8858. Min Act: -0.0000

Data Index: 1091458 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8964. Min Act: -0.0000

Data Index: 118277 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1638408 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1854170 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9271. Min Act: -0.0000

Data Index: 642956 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1121035 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8893. Min Act: -0.0000

Data Index: 816238 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9128. Min Act: -0.0000

Data Index: 184627 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8041. Min Act: -0.0000

Data Index: 921399 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1384959 (The Pile)

Max Activating Token Index: 638

Text #18

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.9089. Min Act: -0.0000

Data Index: 598441 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.2609. Min Range: -1.2609

Max Act: 0.8288. Min Act: -0.0000

Data Index: 462022 (The Pile)

Max Activating Token Index: 874