Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 305 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7332. Min Act: -0.0003

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7759. Min Act: -0.0003

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.8141. Min Act: -0.0003

Data Index: 1057135 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.7227. Min Act: -0.0003

Data Index: 515700 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5598. Min Act: -0.0003

Data Index: 151290 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.6070. Min Act: -0.0003

Data Index: 702363 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.4956. Min Act: -0.0003

Data Index: 611002 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5952. Min Act: -0.0003

Data Index: 1315858 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5948. Min Act: -0.0003

Data Index: 365437 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5913. Min Act: -0.0003

Data Index: 478737 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.4874. Min Act: -0.0003

Data Index: 94093 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5368. Min Act: -0.0003

Data Index: 518847 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5459. Min Act: -0.0003

Data Index: 971605 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5792. Min Act: -0.0003

Data Index: 469348 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5951. Min Act: -0.0003

Data Index: 184878 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5152. Min Act: -0.0003

Data Index: 800154 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.4392. Min Act: -0.0003

Data Index: 778863 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5179. Min Act: -0.0003

Data Index: 795534 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5524. Min Act: -0.0003

Data Index: 817457 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.8141. Min Range: -0.8141

Max Act: 0.5830. Min Act: -0.0003

Data Index: 926730 (C4 (Web Text))

Max Activating Token Index: 587