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

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

Neuron 3813 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.2555. Min Act: -0.0001

Data Index: 703734 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.2479. Min Act: -0.0001

Data Index: 339487 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.3031. Min Act: -0.0001

Data Index: 1127814 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.2227. Min Act: -0.0001

Data Index: 402670 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1053. Min Act: -0.0001

Data Index: 688229 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1251110 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.2547. Min Act: -0.0001

Data Index: 1282501 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1060. Min Act: -0.0001

Data Index: 640270 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1255. Min Act: -0.0001

Data Index: 73630 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1840. Min Act: -0.0001

Data Index: 566782 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.0886. Min Act: -0.0001

Data Index: 1157128 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1710. Min Act: -0.0001

Data Index: 148360 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1768. Min Act: -0.0001

Data Index: 821469 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1037. Min Act: -0.0001

Data Index: 270377 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1612. Min Act: -0.0001

Data Index: 258642 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1379. Min Act: -0.0001

Data Index: 1099822 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.1382. Min Act: -0.0001

Data Index: 988304 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.0641. Min Act: -0.0001

Data Index: 1015372 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.0253. Min Act: -0.0001

Data Index: 710529 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.3031. Min Range: -1.3031

Max Act: 1.0542. Min Act: -0.0001

Data Index: 335559 (C4 (Web Text))

Max Activating Token Index: 300