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

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

Neuron 2605 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: 0.9314. Min Range: -0.9314

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1143273 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8341. Min Act: -0.0001

Data Index: 57928 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7204. Min Act: -0.0000

Data Index: 737865 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1066968 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6794. Min Act: -0.0000

Data Index: 597385 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1238034 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6483. Min Act: -0.0000

Data Index: 239307 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1106946 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6508. Min Act: -0.0000

Data Index: 71547 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6648. Min Act: -0.0000

Data Index: 690837 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6367. Min Act: -0.0000

Data Index: 230284 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6050. Min Act: -0.0000

Data Index: 844849 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1043676 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6238. Min Act: -0.0000

Data Index: 785234 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6588. Min Act: -0.0000

Data Index: 827887 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.5696. Min Act: -0.0000

Data Index: 849370 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.5879. Min Act: -0.0000

Data Index: 536702 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.5878. Min Act: -0.0001

Data Index: 510299 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6053. Min Act: -0.0000

Data Index: 754861 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.5621. Min Act: -0.0000

Data Index: 208778 (C4 (Web Text))

Max Activating Token Index: 547