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

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

Neuron 2410 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4397. Min Act: -0.0000

Data Index: 533304 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4209. Min Act: -0.0001

Data Index: 278707 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4331. Min Act: -0.0000

Data Index: 172829 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1195912 (C4 (Web Text))

Max Activating Token Index: 255

Text #4

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4010. Min Act: -0.0001

Data Index: 1167187 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3907. Min Act: -0.0000

Data Index: 733633 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.4037. Min Act: -0.0001

Data Index: 494910 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3682. Min Act: -0.0001

Data Index: 1044668 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3733. Min Act: -0.0001

Data Index: 351934 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3590. Min Act: -0.0001

Data Index: 441563 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3600. Min Act: -0.0001

Data Index: 1137343 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3356. Min Act: -0.0001

Data Index: 933850 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3415. Min Act: -0.0001

Data Index: 1233838 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3512. Min Act: -0.0000

Data Index: 1251693 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3276. Min Act: -0.0001

Data Index: 917066 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3392. Min Act: -0.0001

Data Index: 717682 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3488. Min Act: -0.0001

Data Index: 320041 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3370. Min Act: -0.0001

Data Index: 1074030 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3216. Min Act: -0.0000

Data Index: 674347 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.4397. Min Range: -0.4397

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1040433 (C4 (Web Text))

Max Activating Token Index: 193