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

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

Neuron 2454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.4616. Min Act: -0.0001

Data Index: 1005600 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.4616. Min Range: -1.4616

Max Act: 1.1788. Min Act: -0.0001

Data Index: 24206 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8827. Min Act: -0.0000

Data Index: 1542790 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8242. Min Act: -0.0000

Data Index: 369283 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8034. Min Act: -0.0001

Data Index: 513691 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7591. Min Act: -0.0001

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8229. Min Act: -0.0001

Data Index: 1032711 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1186072 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7701. Min Act: -0.0001

Data Index: 595071 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7371. Min Act: -0.0001

Data Index: 1246865 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1155515 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7310. Min Act: -0.0000

Data Index: 670978 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.6782. Min Act: -0.0000

Data Index: 214718 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1467566 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7481. Min Act: -0.0001

Data Index: 1198563 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.6863. Min Act: -0.0000

Data Index: 732436 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1081613 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7044. Min Act: -0.0001

Data Index: 761832 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.7275. Min Act: -0.0000

Data Index: 791722 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.4616. Min Range: -1.4616

Max Act: 0.6987. Min Act: -0.0001

Data Index: 1014715 (C4 (Web Text))

Max Activating Token Index: 716