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

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

Neuron 3137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.7112. Min Act: -0.0002

Data Index: 612157 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6771. Min Act: -0.0002

Data Index: 438093 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6136. Min Act: -0.0002

Data Index: 753430 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5887. Min Act: -0.0002

Data Index: 752083 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6432. Min Act: -0.0002

Data Index: 510875 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6168. Min Act: -0.0002

Data Index: 504361 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6207. Min Act: -0.0002

Data Index: 1309333 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5984. Min Act: -0.0002

Data Index: 104065 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5582. Min Act: -0.0002

Data Index: 450426 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6076. Min Act: -0.0002

Data Index: 424004 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5812. Min Act: -0.0002

Data Index: 595710 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5431. Min Act: -0.0002

Data Index: 1133122 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.4912. Min Act: -0.0002

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5583. Min Act: -0.0002

Data Index: 1155829 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6399. Min Act: -0.0002

Data Index: 888772 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6274. Min Act: -0.0002

Data Index: 94342 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5435. Min Act: -0.0002

Data Index: 640312 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5761. Min Act: -0.0002

Data Index: 1197388 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5731. Min Act: -0.0002

Data Index: 1024838 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5345. Min Act: -0.0002

Data Index: 788327 (C4 (Web Text))

Max Activating Token Index: 9