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

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

Neuron 610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0266. Min Range: -2.0266

Max Act: 2.0266. Min Act: -0.0000

Data Index: 1222475 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.9221. Min Act: -0.0000

Data Index: 1242665 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.9005. Min Act: -0.0000

Data Index: 797072 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.8792. Min Act: -0.0000

Data Index: 477012 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7064. Min Act: -0.0000

Data Index: 893649 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1133798 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.8896. Min Act: -0.0000

Data Index: 1305772 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.8426. Min Act: -0.0000

Data Index: 501720 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6335. Min Act: -0.0000

Data Index: 1136902 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5181. Min Act: -0.0000

Data Index: 157161 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.4262. Min Act: -0.0000

Data Index: 982173 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5917. Min Act: -0.0000

Data Index: 465502 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1035662 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.3757. Min Act: -0.0000

Data Index: 442260 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.4247. Min Act: -0.0000

Data Index: 736331 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5089. Min Act: -0.0000

Data Index: 251069 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5696. Min Act: -0.0000

Data Index: 1060007 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.4046. Min Act: -0.0000

Data Index: 458138 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.3814. Min Act: -0.0000

Data Index: 648282 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.5472. Min Act: -0.0000

Data Index: 872067 (C4 (Web Text))

Max Activating Token Index: 517