Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3429. Min Act: -0.0000

Data Index: 309244 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3537. Min Act: -0.0000

Data Index: 958551 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3193. Min Act: -0.0000

Data Index: 602649 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3264. Min Act: -0.0000

Data Index: 482625 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3188. Min Act: -0.0000

Data Index: 820947 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3105. Min Act: -0.0000

Data Index: 307518 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1195993 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.3198. Min Act: -0.0000

Data Index: 461148 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2663. Min Act: -0.0000

Data Index: 381735 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2428. Min Act: -0.0000

Data Index: 1116684 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2322. Min Act: -0.0000

Data Index: 960099 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2250. Min Act: -0.0000

Data Index: 440214 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1272561 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.1982. Min Act: -0.0000

Data Index: 516301 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2129. Min Act: -0.0000

Data Index: 232215 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2140. Min Act: -0.0000

Data Index: 251342 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2063. Min Act: -0.0000

Data Index: 890379 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.1903. Min Act: -0.0000

Data Index: 398028 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.2006. Min Act: -0.0000

Data Index: 193980 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.3537. Min Range: -0.3537

Max Act: 0.1940. Min Act: -0.0000

Data Index: 705857 (C4 (Web Text))

Max Activating Token Index: 585