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

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

Neuron 2663 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.3421. Min Act: -0.0001

Data Index: 257972 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.3337. Min Act: -0.0001

Data Index: 1346346 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2637. Min Act: -0.0001

Data Index: 102515 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1107656 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.2057. Min Act: -0.0001

Data Index: 827904 (C4 (Web Text))

Max Activating Token Index: 880

Text #5

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1995. Min Act: -0.0001

Data Index: 1055355 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1850. Min Act: -0.0001

Data Index: 650566 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1279. Min Act: -0.0001

Data Index: 1023741 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0855. Min Act: -0.0001

Data Index: 386701 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1215. Min Act: -0.0001

Data Index: 555430 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0743. Min Act: -0.0001

Data Index: 954323 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0732. Min Act: -0.0001

Data Index: 430627 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0367. Min Act: -0.0001

Data Index: 214511 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0661. Min Act: -0.0001

Data Index: 764378 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1105. Min Act: -0.0001

Data Index: 962625 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0514. Min Act: -0.0001

Data Index: 364976 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0441. Min Act: -0.0001

Data Index: 515951 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0136. Min Act: -0.0001

Data Index: 1306559 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.1072. Min Act: -0.0001

Data Index: 754220 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 1.3421. Min Range: -1.3421

Max Act: 1.0362. Min Act: -0.0001

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 913