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

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

Neuron 5409 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.5059. Min Act: -0.0000

Data Index: 786533 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4879. Min Act: -0.0000

Data Index: 1241777 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4854. Min Act: -0.0000

Data Index: 53014 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4052. Min Act: -0.0000

Data Index: 1055414 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4438. Min Act: -0.0000

Data Index: 1214496 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4350. Min Act: -0.0000

Data Index: 1157419 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3257. Min Act: -0.0000

Data Index: 225233 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4054. Min Act: -0.0000

Data Index: 443354 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1125255 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3766. Min Act: -0.0000

Data Index: 308826 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3020. Min Act: -0.0000

Data Index: 670524 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1261798 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4134. Min Act: -0.0000

Data Index: 904921 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3315. Min Act: -0.0000

Data Index: 66921 (C4 (Web Text))

Max Activating Token Index: 917

Text #14

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3946. Min Act: -0.0000

Data Index: 206513 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1316179 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.3564. Min Act: -0.0000

Data Index: 444248 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2689. Min Act: -0.0000

Data Index: 66315 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.2572. Min Act: -0.0000

Data Index: 849190 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 1.5059. Min Range: -1.5059

Max Act: 1.4447. Min Act: -0.0000

Data Index: 663230 (C4 (Web Text))

Max Activating Token Index: 846