Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1670 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0004

Data Index: 1017420 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0388. Min Act: -0.0004

Data Index: 1136675 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0374. Min Act: -0.0004

Data Index: 613649 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0389. Min Act: -0.0004

Data Index: 1000300 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0340. Min Act: -0.0004

Data Index: 808469 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0326. Min Act: -0.0004

Data Index: 901025 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0366. Min Act: -0.0004

Data Index: 434584 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0385. Min Act: -0.0004

Data Index: 83560 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0369. Min Act: -0.0004

Data Index: 1178420 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0361. Min Act: -0.0004

Data Index: 678526 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0349. Min Act: -0.0004

Data Index: 782288 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0352. Min Act: -0.0004

Data Index: 112354 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0353. Min Act: -0.0004

Data Index: 590825 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1261885 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0335. Min Act: -0.0004

Data Index: 849928 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0354. Min Act: -0.0004

Data Index: 598216 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0371. Min Act: -0.0004

Data Index: 742432 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0321. Min Act: -0.0004

Data Index: 922346 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0357. Min Act: -0.0004

Data Index: 505738 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0355. Min Act: -0.0004

Data Index: 996316 (C4 (Web Text))

Max Activating Token Index: 444