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

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

Neuron 3809 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1307347 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1085494 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0458. Min Act: -0.0003

Data Index: 351750 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0422. Min Act: -0.0003

Data Index: 781739 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1205107 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0367. Min Act: -0.0003

Data Index: 11812 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0403. Min Act: -0.0003

Data Index: 998028 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0395. Min Act: -0.0003

Data Index: 515778 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0439. Min Act: -0.0003

Data Index: 112135 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1344864 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1056124 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1245374 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1321069 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0376. Min Act: -0.0003

Data Index: 47317 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0367. Min Act: -0.0004

Data Index: 1145248 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0327. Min Act: -0.0003

Data Index: 641502 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0362. Min Act: -0.0003

Data Index: 487151 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0331. Min Act: -0.0003

Data Index: 942644 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0379. Min Act: -0.0003

Data Index: 425253 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.0524. Min Range: -0.0524

Max Act: 0.0376. Min Act: -0.0003

Data Index: 465259 (C4 (Web Text))

Max Activating Token Index: 791