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

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

Neuron 2192 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0366. Min Range: -2.0366

Max Act: 2.0366. Min Act: -0.0000

Data Index: 224108 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.8446. Min Act: -0.0000

Data Index: 1032634 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.7187. Min Act: -0.0000

Data Index: 32019 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1214050 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.5634. Min Act: -0.0000

Data Index: 575227 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.4500. Min Act: -0.0000

Data Index: 924329 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.5202. Min Act: -0.0000

Data Index: 826882 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.2708. Min Act: -0.0000

Data Index: 638471 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.3809. Min Act: -0.0000

Data Index: 223489 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1251222 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.2346. Min Act: -0.0000

Data Index: 41575 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.1552. Min Act: -0.0000

Data Index: 310526 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1135571 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.2890. Min Act: -0.0000

Data Index: 1063384 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.2084. Min Act: -0.0000

Data Index: 376438 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.1964. Min Act: -0.0000

Data Index: 962700 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.1261. Min Act: -0.0000

Data Index: 1358268 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.1798. Min Act: -0.0000

Data Index: 721995 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 2.0366. Min Range: -2.0366

Max Act: 0.9925. Min Act: -0.0000

Data Index: 617796 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 2.0366. Min Range: -2.0366

Max Act: 1.0966. Min Act: -0.0000

Data Index: 434122 (C4 (Web Text))

Max Activating Token Index: 853