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

Dataset: The Pile

Neuron 3686 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1204. Min Range: -1.1204

Max Act: 1.0669. Min Act: -0.0000

Data Index: 924295 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 1.1204. Min Range: -1.1204

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1420462 (The Pile)

Max Activating Token Index: 980

Text #2

Max Range: 1.1204. Min Range: -1.1204

Max Act: 1.0607. Min Act: -0.0000

Data Index: 205500 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 1.1204. Min Range: -1.1204

Max Act: 1.0459. Min Act: -0.0000

Data Index: 184335 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.9943. Min Act: 0.0000

Data Index: 1532820 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.9392. Min Act: -0.0000

Data Index: 73250 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1836430 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.9557. Min Act: 0.0000

Data Index: 1984278 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1991438 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1653643 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1394181 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8310. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8616. Min Act: -0.0000

Data Index: 291076 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1776578 (The Pile)

Max Activating Token Index: 782

Text #14

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1848973 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8363. Min Act: 0.0000

Data Index: 1809580 (The Pile)

Max Activating Token Index: 110

Text #16

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8059. Min Act: -0.0000

Data Index: 317826 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8216. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1961807 (The Pile)

Max Activating Token Index: 225

Text #19

Max Range: 1.1204. Min Range: -1.1204

Max Act: 0.8095. Min Act: -0.0000

Data Index: 660737 (The Pile)

Max Activating Token Index: 220