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

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

Neuron 885 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1444. Min Act: -0.0002

Data Index: 774684 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.1469. Min Act: -0.0002

Data Index: 825683 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0738. Min Act: -0.0002

Data Index: 257834 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0738. Min Act: -0.0002

Data Index: 696966 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0920. Min Act: -0.0002

Data Index: 1060930 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0778. Min Act: -0.0002

Data Index: 902311 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0713. Min Act: -0.0002

Data Index: 175771 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0651. Min Act: -0.0002

Data Index: 296975 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0060. Min Act: -0.0002

Data Index: 714243 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0426. Min Act: -0.0002

Data Index: 1334026 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0253. Min Act: -0.0002

Data Index: 1123761 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0371. Min Act: -0.0002

Data Index: 1159775 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0115. Min Act: -0.0002

Data Index: 729309 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0508. Min Act: -0.0002

Data Index: 996511 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0230. Min Act: -0.0002

Data Index: 1102704 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0140. Min Act: -0.0002

Data Index: 859916 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0278. Min Act: -0.0002

Data Index: 1128397 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0264. Min Act: -0.0002

Data Index: 69205 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0162. Min Act: -0.0002

Data Index: 185613 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 1.1469. Min Range: -1.1469

Max Act: 1.0225. Min Act: -0.0002

Data Index: 1106450 (C4 (Web Text))

Max Activating Token Index: 249