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

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

Neuron 1564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0409. Min Act: -0.0001

Data Index: 481173 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0001

Data Index: 329443 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1151760 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0392. Min Act: -0.0001

Data Index: 55494 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0399. Min Act: -0.0002

Data Index: 340339 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1151841 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0361. Min Act: -0.0002

Data Index: 32176 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1337250 (C4 (Web Text))

Max Activating Token Index: 1017

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0330. Min Act: -0.0002

Data Index: 811842 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0368. Min Act: -0.0002

Data Index: 157660 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0370. Min Act: -0.0001

Data Index: 1288157 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0315. Min Act: -0.0001

Data Index: 742627 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0352. Min Act: -0.0002

Data Index: 222612 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1119671 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0348. Min Act: -0.0001

Data Index: 634190 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0322. Min Act: -0.0001

Data Index: 522117 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0371. Min Act: -0.0001

Data Index: 655884 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0342. Min Act: -0.0001

Data Index: 284202 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1286095 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0361. Min Act: -0.0002

Data Index: 126631 (C4 (Web Text))

Max Activating Token Index: 68