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

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

Neuron 3500 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0441. Min Act: -0.0002

Data Index: 885097 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1271473 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0405. Min Act: -0.0002

Data Index: 157692 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0365. Min Act: -0.0002

Data Index: 312293 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0363. Min Act: -0.0001

Data Index: 644525 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0356. Min Act: -0.0002

Data Index: 741319 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1311682 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0345. Min Act: -0.0002

Data Index: 533077 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1030468 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0323. Min Act: -0.0002

Data Index: 678389 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0322. Min Act: -0.0002

Data Index: 349266 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0335. Min Act: -0.0002

Data Index: 298932 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0325. Min Act: -0.0001

Data Index: 315826 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1182213 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0323. Min Act: -0.0002

Data Index: 639797 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0316. Min Act: -0.0002

Data Index: 423904 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1065251 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0316. Min Act: -0.0001

Data Index: 991704 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.0441. Min Range: -0.0441

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1241590 (C4 (Web Text))

Max Activating Token Index: 677