Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1331928 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0447. Min Act: -0.0000

Data Index: 1216353 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0438. Min Act: -0.0000

Data Index: 953062 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0450. Min Act: -0.0000

Data Index: 207947 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0422. Min Act: -0.0000

Data Index: 1228057 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0414. Min Act: -0.0000

Data Index: 181149 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1036879 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1151017 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0377. Min Act: -0.0000

Data Index: 632647 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0382. Min Act: -0.0000

Data Index: 645400 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0396. Min Act: -0.0000

Data Index: 686312 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0350. Min Act: -0.0000

Data Index: 1279708 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1360953 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0359. Min Act: -0.0000

Data Index: 833165 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0342. Min Act: -0.0000

Data Index: 867183 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1640128 (Python Code)

Max Activating Token Index: 574

Text #16

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0330. Min Act: -0.0000

Data Index: 468820 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0335. Min Act: -0.0000

Data Index: 868649 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1255851 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.0509. Min Range: -0.0509

Max Act: 0.0335. Min Act: -0.0000

Data Index: 916746 (C4 (Web Text))

Max Activating Token Index: 446