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

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

Neuron 3117 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: 4.4212. Min Range: -4.4212

Max Act: 4.4212. Min Act: -0.0000

Data Index: 1069699 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 4.4212. Min Range: -4.4212

Max Act: 4.2471. Min Act: -0.0000

Data Index: 963139 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 4.4212. Min Range: -4.4212

Max Act: 4.0918. Min Act: -0.0000

Data Index: 324543 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 4.4212. Min Range: -4.4212

Max Act: 4.2422. Min Act: -0.0000

Data Index: 302359 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 4.4212. Min Range: -4.4212

Max Act: 4.1019. Min Act: -0.0000

Data Index: 67172 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.9231. Min Act: -0.0000

Data Index: 1133971 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.6857. Min Act: -0.0000

Data Index: 753460 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.8919. Min Act: -0.0000

Data Index: 708968 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.7644. Min Act: -0.0000

Data Index: 962351 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.6042. Min Act: -0.0000

Data Index: 68927 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.5600. Min Act: -0.0000

Data Index: 528639 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.3175. Min Act: -0.0000

Data Index: 631553 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.3348. Min Act: -0.0000

Data Index: 868171 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.4192. Min Act: -0.0000

Data Index: 488344 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.4364. Min Act: -0.0000

Data Index: 945132 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.2337. Min Act: -0.0000

Data Index: 1191553 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.5250. Min Act: -0.0000

Data Index: 351851 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.3428. Min Act: -0.0000

Data Index: 281081 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.1824. Min Act: -0.0000

Data Index: 1244432 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 4.4212. Min Range: -4.4212

Max Act: 3.4469. Min Act: -0.0000

Data Index: 921103 (C4 (Web Text))

Max Activating Token Index: 35