Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2866 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.2181. Min Act: -0.0000

Data Index: 230770 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 1.2181. Min Range: -1.2181

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1136443 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8977. Min Act: -0.0000

Data Index: 331222 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8620. Min Act: -0.0000

Data Index: 237107 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8591. Min Act: -0.0000

Data Index: 851907 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8649. Min Act: -0.0000

Data Index: 675965 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8546. Min Act: -0.0000

Data Index: 34765 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8536. Min Act: -0.0000

Data Index: 855928 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1130486 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8150. Min Act: -0.0000

Data Index: 41019 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1239239 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8020. Min Act: -0.0000

Data Index: 335844 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8408. Min Act: -0.0000

Data Index: 147499 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1199438 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1154503 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1228677 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7532. Min Act: -0.0000

Data Index: 680774 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7417. Min Act: -0.0000

Data Index: 366498 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7227. Min Act: -0.0000

Data Index: 502197 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.2181. Min Range: -1.2181

Max Act: 0.7212. Min Act: -0.0000

Data Index: 347566 (C4 (Web Text))

Max Activating Token Index: 521