Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3916 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8951. Min Act: -0.0001

Data Index: 251204 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8343. Min Act: -0.0001

Data Index: 198022 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8241. Min Act: -0.0001

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8001. Min Act: -0.0001

Data Index: 212722 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8298. Min Act: -0.0001

Data Index: 364964 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7701. Min Act: -0.0001

Data Index: 396205 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7801. Min Act: -0.0001

Data Index: 785780 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7667. Min Act: -0.0001

Data Index: 1272125 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7589. Min Act: -0.0001

Data Index: 52015 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7327. Min Act: -0.0001

Data Index: 457587 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.8193. Min Act: -0.0001

Data Index: 1219616 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7390. Min Act: -0.0001

Data Index: 1042920 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6883. Min Act: -0.0001

Data Index: 908224 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7048. Min Act: -0.0001

Data Index: 943446 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6965. Min Act: -0.0001

Data Index: 855602 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6981. Min Act: -0.0001

Data Index: 1209293 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7086. Min Act: -0.0001

Data Index: 695057 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7108. Min Act: -0.0001

Data Index: 953932 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.7054. Min Act: -0.0001

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.8951. Min Range: -0.8951

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1069877 (C4 (Web Text))

Max Activating Token Index: 805