Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.2200. Min Act: -0.0000

Data Index: 404928 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.1982. Min Act: -0.0000

Data Index: 426388 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.2428. Min Act: -0.0000

Data Index: 769930 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.2080. Min Act: -0.0000

Data Index: 416221 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0426. Min Act: -0.0000

Data Index: 710482 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1216811 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1016652 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.1285. Min Act: -0.0000

Data Index: 1096331 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1182403 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1023755 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0554. Min Act: -0.0000

Data Index: 984761 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0443. Min Act: -0.0000

Data Index: 172475 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 1.2428. Min Range: -1.2428

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1107594 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0103. Min Act: -0.0000

Data Index: 122237 (C4 (Web Text))

Max Activating Token Index: 181

Text #14

Max Range: 1.2428. Min Range: -1.2428

Max Act: 0.9508. Min Act: -0.0000

Data Index: 506409 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.2428. Min Range: -1.2428

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1137585 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0177. Min Act: -0.0000

Data Index: 367804 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.2428. Min Range: -1.2428

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1043771 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.2428. Min Range: -1.2428

Max Act: 0.9689. Min Act: -0.0000

Data Index: 39099 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.2428. Min Range: -1.2428

Max Act: 0.9862. Min Act: -0.0000

Data Index: 462791 (C4 (Web Text))

Max Activating Token Index: 406