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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.4060. Min Act: -0.0001

Data Index: 488261 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3837. Min Act: -0.0000

Data Index: 1078069 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3757. Min Act: -0.0000

Data Index: 153001 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1291475 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3659. Min Act: 0.0001

Data Index: 1222546 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.3009. Min Act: 0.0000

Data Index: 169087 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2520. Min Act: -0.0000

Data Index: 1338613 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2359. Min Act: -0.0000

Data Index: 983175 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2360. Min Act: -0.0001

Data Index: 120025 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2172. Min Act: -0.0000

Data Index: 344159 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2281. Min Act: -0.0000

Data Index: 654257 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1347301 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2232. Min Act: -0.0001

Data Index: 1319564 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2104. Min Act: -0.0000

Data Index: 809494 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.2187. Min Act: -0.0000

Data Index: 330681 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.1987. Min Act: -0.0000

Data Index: 531390 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.1995. Min Act: -0.0000

Data Index: 86955 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1308464 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.1977. Min Act: 0.0000

Data Index: 405351 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.4060. Min Range: -0.4060

Max Act: 0.1854. Min Act: 0.0000

Data Index: 469384 (C4 (Web Text))

Max Activating Token Index: 254