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

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

Neuron 2198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.1903. Min Act: -0.0000

Data Index: 374787 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.3231. Min Act: -0.0001

Data Index: 695384 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.2240. Min Act: -0.0001

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.3612. Min Act: -0.0000

Data Index: 900159 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.0341. Min Act: -0.0001

Data Index: 28324 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.0979. Min Act: -0.0001

Data Index: 894756 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 4.3612. Min Range: -4.3612

Max Act: 4.2774. Min Act: -0.0000

Data Index: 702199 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.9141. Min Act: -0.0000

Data Index: 446351 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.9083. Min Act: -0.0001

Data Index: 374015 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.8882. Min Act: -0.0001

Data Index: 288227 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.9276. Min Act: -0.0001

Data Index: 280518 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.5712. Min Act: -0.0001

Data Index: 1036213 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.9174. Min Act: -0.0000

Data Index: 145153 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.5873. Min Act: -0.0001

Data Index: 1028122 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.9164. Min Act: -0.0000

Data Index: 871493 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.8558. Min Act: -0.0000

Data Index: 1339492 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.8590. Min Act: -0.0000

Data Index: 869029 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.8690. Min Act: -0.0000

Data Index: 1304638 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.8468. Min Act: -0.0000

Data Index: 184180 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 4.3612. Min Range: -4.3612

Max Act: 3.6192. Min Act: -0.0001

Data Index: 1236876 (C4 (Web Text))

Max Activating Token Index: 886