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

Dataset: The Pile

Neuron 5051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.3221. Min Act: -0.0000

Data Index: 13974 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2947. Min Act: -0.0000

Data Index: 1553770 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2933. Min Act: -0.0000

Data Index: 1335126 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2102. Min Act: -0.0000

Data Index: 364563 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0442. Min Act: -0.0000

Data Index: 1327123 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0972. Min Act: -0.0000

Data Index: 1941408 (The Pile)

Max Activating Token Index: 911

Text #6

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0314. Min Act: -0.0000

Data Index: 1167443 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.8096. Min Act: -0.0000

Data Index: 940567 (The Pile)

Max Activating Token Index: 1021

Text #8

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.8759. Min Act: -0.0000

Data Index: 1312256 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.7845. Min Act: -0.0000

Data Index: 1010888 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.8845. Min Act: -0.0000

Data Index: 1330620 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.7459. Min Act: -0.0000

Data Index: 906301 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.5948. Min Act: -0.0000

Data Index: 1140063 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.7061. Min Act: -0.0000

Data Index: 1964698 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.5510. Min Act: -0.0000

Data Index: 1336746 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.7868. Min Act: -0.0000

Data Index: 402836 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.5085. Min Act: -0.0000

Data Index: 1422381 (The Pile)

Max Activating Token Index: 951

Text #17

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.6214. Min Act: -0.0000

Data Index: 1316894 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.6092. Min Act: -0.0000

Data Index: 289591 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.5868. Min Act: -0.0000

Data Index: 84352 (The Pile)

Max Activating Token Index: 486