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

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

Neuron 1149 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3860. Min Act: -0.0002

Data Index: 519571 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3319. Min Act: -0.0002

Data Index: 542112 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2764. Min Act: -0.0002

Data Index: 470040 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3223. Min Act: -0.0002

Data Index: 559195 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3156. Min Act: -0.0002

Data Index: 1186245 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2938. Min Act: -0.0002

Data Index: 1292027 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3039. Min Act: -0.0002

Data Index: 1070878 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3139. Min Act: -0.0002

Data Index: 317695 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2755. Min Act: -0.0002

Data Index: 85146 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3331. Min Act: -0.0002

Data Index: 769109 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3257. Min Act: -0.0002

Data Index: 494450 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3324. Min Act: -0.0002

Data Index: 64366 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2958. Min Act: -0.0002

Data Index: 788592 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2974. Min Act: -0.0002

Data Index: 1059825 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2582. Min Act: -0.0002

Data Index: 742020 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3461. Min Act: -0.0002

Data Index: 670622 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3097. Min Act: -0.0002

Data Index: 732429 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3446. Min Act: -0.0002

Data Index: 981571 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3663. Min Act: -0.0002

Data Index: 1137520 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2794. Min Act: -0.0002

Data Index: 540385 (C4 (Web Text))

Max Activating Token Index: 864