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

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

Neuron 1624 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: 1.4925. Min Range: -1.4925

Max Act: 1.4751. Min Act: -0.0000

Data Index: 328872 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.4925. Min Act: -0.0000

Data Index: 949538 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.2487. Min Act: 0.0000

Data Index: 810931 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1504. Min Act: -0.0000

Data Index: 298623 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1171. Min Act: -0.0000

Data Index: 1415421 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 1.4925. Min Range: -1.4925

Max Act: 0.9841. Min Act: -0.0000

Data Index: 567799 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1215. Min Act: -0.0000

Data Index: 851545 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0634. Min Act: -0.0000

Data Index: 880333 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.1247. Min Act: -0.0000

Data Index: 214118 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0469. Min Act: -0.0000

Data Index: 999380 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0800. Min Act: -0.0000

Data Index: 161407 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1211565 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0277. Min Act: -0.0000

Data Index: 137938 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0375. Min Act: -0.0000

Data Index: 1063043 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0611. Min Act: -0.0000

Data Index: 859825 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0143. Min Act: -0.0000

Data Index: 1219936 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0022. Min Act: -0.0000

Data Index: 386550 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0196. Min Act: -0.0000

Data Index: 1216645 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0342. Min Act: -0.0000

Data Index: 37524 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 1.4925. Min Range: -1.4925

Max Act: 1.0029. Min Act: -0.0000

Data Index: 901723 (C4 (Web Text))

Max Activating Token Index: 851