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

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

Neuron 3613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.6464. Min Act: -0.0002

Data Index: 649111 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.5861. Min Act: -0.0002

Data Index: 109746 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4929. Min Act: -0.0002

Data Index: 688605 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.3676. Min Act: -0.0002

Data Index: 523923 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.2414. Min Act: -0.0002

Data Index: 183970 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.2395. Min Act: -0.0002

Data Index: 558988 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.2111. Min Act: -0.0002

Data Index: 1074160 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.2126. Min Act: -0.0002

Data Index: 1173820 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.2214. Min Act: -0.0002

Data Index: 977473 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1676. Min Act: -0.0002

Data Index: 713822 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1604. Min Act: -0.0002

Data Index: 1029054 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1611. Min Act: -0.0002

Data Index: 1155585 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1512. Min Act: -0.0002

Data Index: 686077 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1143. Min Act: -0.0002

Data Index: 1245406 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1831. Min Act: -0.0002

Data Index: 553477 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.0995. Min Act: -0.0002

Data Index: 64520 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1335. Min Act: -0.0002

Data Index: 359206 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1274. Min Act: -0.0002

Data Index: 307809 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1513. Min Act: -0.0002

Data Index: 498107 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.1204. Min Act: -0.0002

Data Index: 918301 (C4 (Web Text))

Max Activating Token Index: 41