Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 868 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0403. Min Act: -0.0003

Data Index: 641697 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1234481 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1140888 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0330. Min Act: -0.0003

Data Index: 248618 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0327. Min Act: -0.0003

Data Index: 642296 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1316571 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1289847 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0327. Min Act: -0.0003

Data Index: 400409 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0323. Min Act: -0.0003

Data Index: 352640 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0325. Min Act: -0.0003

Data Index: 209374 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0315. Min Act: -0.0002

Data Index: 143210 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0307. Min Act: -0.0003

Data Index: 214409 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0322. Min Act: -0.0003

Data Index: 253092 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0309. Min Act: -0.0003

Data Index: 200170 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0312. Min Act: -0.0003

Data Index: 597655 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0313. Min Act: -0.0003

Data Index: 952082 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0306. Min Act: -0.0004

Data Index: 1055440 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0313. Min Act: -0.0003

Data Index: 422838 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0302. Min Act: -0.0003

Data Index: 104082 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0307. Min Act: -0.0002

Data Index: 874918 (C4 (Web Text))

Max Activating Token Index: 160