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

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

Neuron 670 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6048. Min Act: -0.0000

Data Index: 228928 (C4 (Web Text))

Max Activating Token Index: 304

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1172907 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1161343 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5569. Min Act: -0.0000

Data Index: 955258 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5921. Min Act: -0.0000

Data Index: 637424 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1007984 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5126. Min Act: -0.0000

Data Index: 22111 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1260488 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5086. Min Act: -0.0000

Data Index: 525016 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1267046 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4814. Min Act: -0.0000

Data Index: 127496 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5258. Min Act: -0.0000

Data Index: 571828 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4678. Min Act: -0.0000

Data Index: 240879 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1214401 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4757. Min Act: -0.0000

Data Index: 1262865 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4413. Min Act: -0.0000

Data Index: 297541 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4859. Min Act: -0.0000

Data Index: 760931 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4411. Min Act: -0.0000

Data Index: 602006 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4613. Min Act: -0.0000

Data Index: 44957 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4531. Min Act: -0.0000

Data Index: 443963 (C4 (Web Text))

Max Activating Token Index: 315