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

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

Neuron 3882 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0986. Min Act: -0.0000

Data Index: 629455 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1096301 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0522. Min Act: -0.0000

Data Index: 348290 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1288780 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9275. Min Act: -0.0000

Data Index: 1013482 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.9268. Min Act: -0.0000

Data Index: 573017 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1119338 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 1.0986. Min Range: -1.0986

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1335292 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.8324. Min Act: -0.0000

Data Index: 406527 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.7670. Min Act: -0.0000

Data Index: 942443 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.7789. Min Act: -0.0000

Data Index: 781099 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6923. Min Act: -0.0000

Data Index: 951839 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.7118. Min Act: -0.0000

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1267952 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6501. Min Act: -0.0000

Data Index: 145589 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6749. Min Act: -0.0000

Data Index: 136682 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6278. Min Act: -0.0000

Data Index: 488573 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6408. Min Act: -0.0000

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6162. Min Act: -0.0000

Data Index: 209266 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.0986. Min Range: -1.0986

Max Act: 0.6263. Min Act: -0.0000

Data Index: 230882 (C4 (Web Text))

Max Activating Token Index: 504