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

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

Neuron 1706 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.1221. Min Act: -0.0001

Data Index: 319774 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.0077. Min Act: -0.0001

Data Index: 524350 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9272. Min Act: -0.0001

Data Index: 723484 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8847. Min Act: -0.0001

Data Index: 679080 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8813. Min Act: -0.0001

Data Index: 556350 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9119. Min Act: -0.0001

Data Index: 421039 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9297. Min Act: -0.0001

Data Index: 581930 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.1221. Min Range: -1.1221

Max Act: 1.0073. Min Act: -0.0001

Data Index: 1033305 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8298. Min Act: -0.0001

Data Index: 1252641 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7725. Min Act: -0.0001

Data Index: 297018 (C4 (Web Text))

Max Activating Token Index: 341

Text #10

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7677. Min Act: -0.0001

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7893. Min Act: -0.0001

Data Index: 927432 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7550. Min Act: -0.0001

Data Index: 918207 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1212127 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8096. Min Act: -0.0001

Data Index: 859967 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7864. Min Act: -0.0001

Data Index: 460110 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7903. Min Act: -0.0001

Data Index: 831241 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7027. Min Act: -0.0001

Data Index: 525952 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.6479. Min Act: -0.0001

Data Index: 940683 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7238. Min Act: -0.0001

Data Index: 426195 (C4 (Web Text))

Max Activating Token Index: 801