Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3388 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2735. Min Act: -0.0001

Data Index: 1029596 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2330. Min Act: -0.0000

Data Index: 939288 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2584. Min Act: -0.0001

Data Index: 432296 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2423. Min Act: -0.0000

Data Index: 509557 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2341. Min Act: -0.0001

Data Index: 1255523 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2212. Min Act: -0.0000

Data Index: 888292 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2197. Min Act: -0.0000

Data Index: 515607 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2251. Min Act: -0.0001

Data Index: 764464 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2265. Min Act: -0.0001

Data Index: 541732 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2119. Min Act: -0.0000

Data Index: 730216 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2241. Min Act: -0.0000

Data Index: 208773 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2174. Min Act: -0.0000

Data Index: 779228 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2196. Min Act: -0.0001

Data Index: 894177 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2009. Min Act: -0.0000

Data Index: 594038 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2097. Min Act: -0.0001

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1356211 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1995. Min Act: -0.0001

Data Index: 277407 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1993. Min Act: -0.0000

Data Index: 52257 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.1750. Min Act: -0.0000

Data Index: 670439 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2151. Min Act: -0.0001

Data Index: 576953 (C4 (Web Text))

Max Activating Token Index: 312