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

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

Neuron 3878 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6152. Min Act: -0.0000

Data Index: 1045288 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6204. Min Act: -0.0000

Data Index: 8819 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.6514. Min Act: -0.0000

Data Index: 999389 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5820. Min Act: -0.0000

Data Index: 487962 (C4 (Web Text))

Max Activating Token Index: 484

Text #4

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1192373 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5699. Min Act: -0.0000

Data Index: 684976 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5639. Min Act: -0.0000

Data Index: 347137 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5077. Min Act: -0.0000

Data Index: 213994 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1033529 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5308. Min Act: -0.0000

Data Index: 463405 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5527. Min Act: -0.0000

Data Index: 312508 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5129. Min Act: -0.0000

Data Index: 185250 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5290. Min Act: -0.0000

Data Index: 1170933 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5402. Min Act: -0.0000

Data Index: 267483 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5234. Min Act: -0.0000

Data Index: 47514 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5316. Min Act: -0.0000

Data Index: 1228424 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4932. Min Act: -0.0000

Data Index: 849457 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4921. Min Act: -0.0000

Data Index: 412754 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.4904. Min Act: -0.0000

Data Index: 226502 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.6514. Min Range: -0.6514

Max Act: 0.5264. Min Act: -0.0000

Data Index: 594595 (C4 (Web Text))

Max Activating Token Index: 792