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

Dataset: The Pile

Neuron 2835 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.4037. Min Act: -0.0001

Data Index: 1167471 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1220851 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1920449 (The Pile)

Max Activating Token Index: 417

Text #3

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1129963 (The Pile)

Max Activating Token Index: 275

Text #4

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.3160. Min Act: -0.0001

Data Index: 8356 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2823. Min Act: -0.0000

Data Index: 147269 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2744. Min Act: -0.0000

Data Index: 1431678 (The Pile)

Max Activating Token Index: 353

Text #7

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2757. Min Act: -0.0000

Data Index: 1735537 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1541463 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2335. Min Act: -0.0001

Data Index: 514086 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2536. Min Act: -0.0000

Data Index: 123762 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2191. Min Act: -0.0000

Data Index: 33105 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1515458 (The Pile)

Max Activating Token Index: 304

Text #13

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2217. Min Act: -0.0001

Data Index: 161325 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1449463 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2262. Min Act: -0.0001

Data Index: 921077 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2351. Min Act: -0.0000

Data Index: 758401 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.1924. Min Act: -0.0001

Data Index: 1687476 (The Pile)

Max Activating Token Index: 637

Text #18

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2269. Min Act: -0.0001

Data Index: 724221 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 0.4037. Min Range: -0.4037

Max Act: 0.2176. Min Act: -0.0000

Data Index: 42323 (The Pile)

Max Activating Token Index: 478