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

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

Neuron 4723 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: 4.1141. Min Range: -4.1141

Max Act: 4.1141. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 4.1141. Min Range: -4.1141

Max Act: 3.6776. Min Act: -0.0000

Data Index: 899111 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 4.1141. Min Range: -4.1141

Max Act: 3.3125. Min Act: -0.0000

Data Index: 191049 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.9934. Min Act: -0.0000

Data Index: 267403 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 4.1141. Min Range: -4.1141

Max Act: 3.0962. Min Act: -0.0000

Data Index: 579420 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1046743 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.9068. Min Act: -0.0000

Data Index: 854817 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.6176. Min Act: -0.0000

Data Index: 968774 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.7956. Min Act: -0.0000

Data Index: 257974 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.8176. Min Act: -0.0000

Data Index: 1000390 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.8473. Min Act: -0.0000

Data Index: 1173921 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.3281. Min Act: -0.0000

Data Index: 465695 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.5814. Min Act: -0.0000

Data Index: 1021702 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.6202. Min Act: -0.0000

Data Index: 689132 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.6378. Min Act: -0.0000

Data Index: 1181084 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.4847. Min Act: -0.0000

Data Index: 1301919 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.6376. Min Act: -0.0000

Data Index: 305642 (C4 (Web Text))

Max Activating Token Index: 432

Text #17

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.5006. Min Act: -0.0000

Data Index: 480963 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.4770. Min Act: -0.0000

Data Index: 559039 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.1141. Min Range: -4.1141

Max Act: 2.6117. Min Act: -0.0000

Data Index: 318505 (C4 (Web Text))

Max Activating Token Index: 87