Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1126 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2735. Min Act: -0.0001

Data Index: 478322 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2741. Min Act: -0.0001

Data Index: 503441 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2554. Min Act: -0.0001

Data Index: 960845 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2608. Min Act: -0.0001

Data Index: 649822 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1205769 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2631. Min Act: -0.0001

Data Index: 1287851 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2369. Min Act: -0.0001

Data Index: 717103 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1224972 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2447. Min Act: -0.0001

Data Index: 511433 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2338. Min Act: -0.0001

Data Index: 894512 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2377. Min Act: -0.0000

Data Index: 853023 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2608. Min Act: -0.0000

Data Index: 662607 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1156371 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2327. Min Act: -0.0000

Data Index: 490588 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2329. Min Act: -0.0001

Data Index: 1082270 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1296645 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2254. Min Act: -0.0000

Data Index: 406445 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2167. Min Act: -0.0001

Data Index: 223877 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2312. Min Act: -0.0001

Data Index: 542531 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2309. Min Act: -0.0001

Data Index: 1240085 (C4 (Web Text))

Max Activating Token Index: 474