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

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

Neuron 4784 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: 0.5306. Min Range: -0.5306

Max Act: 0.5306. Min Act: -0.0000

Data Index: 88429 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4865. Min Act: -0.0000

Data Index: 221041 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4416. Min Act: -0.0000

Data Index: 359176 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1113979 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4214. Min Act: -0.0000

Data Index: 79651 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4016. Min Act: -0.0000

Data Index: 950329 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3948. Min Act: -0.0000

Data Index: 151136 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.4009. Min Act: -0.0000

Data Index: 422690 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3753. Min Act: -0.0000

Data Index: 205856 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3427. Min Act: -0.0000

Data Index: 884209 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3471. Min Act: -0.0000

Data Index: 257876 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1078711 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1211106 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1033294 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1150821 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3272. Min Act: -0.0000

Data Index: 964601 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3152. Min Act: -0.0001

Data Index: 48114 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3386. Min Act: -0.0000

Data Index: 906874 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3347. Min Act: -0.0000

Data Index: 137371 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.5306. Min Range: -0.5306

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1069664 (C4 (Web Text))

Max Activating Token Index: 506