Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1276712 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5582. Min Act: -0.0000

Data Index: 400338 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1924069 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1677162 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4939. Min Act: -0.0000

Data Index: 692572 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1275713 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1219743 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4584. Min Act: -0.0000

Data Index: 580419 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1974562 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1232438 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1079492 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1995499 (The Pile)

Max Activating Token Index: 168

Text #12

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1831978 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1497177 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4309. Min Act: -0.0000

Data Index: 728538 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5358. Min Act: -0.0000

Data Index: 261252 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4258. Min Act: -0.0000

Data Index: 398242 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4006. Min Act: -0.0000

Data Index: 212891 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.4184. Min Act: -0.0000

Data Index: 1788280 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.6271. Min Range: -0.6271

Max Act: 0.5045. Min Act: -0.0000

Data Index: 22235 (The Pile)

Max Activating Token Index: 178