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

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

Neuron 952 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: 5.2020. Min Range: -5.2020

Max Act: 5.2020. Min Act: -0.0000

Data Index: 339450 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 5.2020. Min Range: -5.2020

Max Act: 5.0235. Min Act: -0.0000

Data Index: 950309 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 5.2020. Min Range: -5.2020

Max Act: 5.1547. Min Act: -0.0000

Data Index: 649227 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.7505. Min Act: -0.0000

Data Index: 466681 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.8884. Min Act: -0.0000

Data Index: 844531 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.6504. Min Act: -0.0000

Data Index: 64519 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.9498. Min Act: -0.0000

Data Index: 951571 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.6378. Min Act: -0.0000

Data Index: 272362 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.4378. Min Act: -0.0000

Data Index: 1206378 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.5866. Min Act: -0.0000

Data Index: 790676 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.7313. Min Act: -0.0000

Data Index: 959790 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.5478. Min Act: -0.0000

Data Index: 99371 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.2808. Min Act: -0.0000

Data Index: 93060 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.6347. Min Act: -0.0000

Data Index: 177255 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.2676. Min Act: -0.0000

Data Index: 30266 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.4484. Min Act: -0.0000

Data Index: 723537 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 5.2020. Min Range: -5.2020

Max Act: 3.9419. Min Act: -0.0000

Data Index: 643006 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.5928. Min Act: -0.0000

Data Index: 120225 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.4272. Min Act: -0.0000

Data Index: 1041907 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 5.2020. Min Range: -5.2020

Max Act: 4.7351. Min Act: -0.0000

Data Index: 555102 (C4 (Web Text))

Max Activating Token Index: 57