Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1578 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0438. Min Act: -0.0003

Data Index: 745871 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0409. Min Act: -0.0003

Data Index: 212259 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1099069 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1077933 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0360. Min Act: -0.0004

Data Index: 925417 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0368. Min Act: -0.0003

Data Index: 331280 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0357. Min Act: -0.0004

Data Index: 1154378 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1058301 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0363. Min Act: -0.0004

Data Index: 792429 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0343. Min Act: -0.0003

Data Index: 514814 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0351. Min Act: -0.0004

Data Index: 22341 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0346. Min Act: -0.0004

Data Index: 257718 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0348. Min Act: -0.0003

Data Index: 997956 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0356. Min Act: -0.0003

Data Index: 563789 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0353. Min Act: -0.0003

Data Index: 613773 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0360. Min Act: -0.0003

Data Index: 313242 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1132041 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0333. Min Act: -0.0004

Data Index: 672299 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0327. Min Act: -0.0004

Data Index: 224143 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0438. Min Range: -0.0438

Max Act: 0.0341. Min Act: -0.0004

Data Index: 657206 (C4 (Web Text))

Max Activating Token Index: 100