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

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

Neuron 259 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.6962. Min Act: -0.0000

Data Index: 767726 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.5912. Min Act: -0.0000

Data Index: 1226384 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.3914. Min Act: -0.0000

Data Index: 170836 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.4124. Min Act: -0.0000

Data Index: 951660 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1263459 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.1358. Min Act: -0.0000

Data Index: 1240292 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.1490. Min Act: -0.0000

Data Index: 215707 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.1800. Min Act: -0.0000

Data Index: 822735 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 1.6962. Min Range: -1.6962

Max Act: 1.1076. Min Act: -0.0000

Data Index: 756698 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9520. Min Act: -0.0000

Data Index: 639551 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1336528 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9040. Min Act: -0.0000

Data Index: 933296 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9255. Min Act: -0.0000

Data Index: 1231535 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9146. Min Act: -0.0000

Data Index: 778908 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1254310 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9480. Min Act: -0.0000

Data Index: 509553 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.9335. Min Act: -0.0000

Data Index: 240099 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1595125 (Python Code)

Max Activating Token Index: 980

Text #19

Max Range: 1.6962. Min Range: -1.6962

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1558133 (Python Code)

Max Activating Token Index: 118