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

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

Neuron 333 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: 0.0437. Min Range: -0.0437

Max Act: 0.0437. Min Act: -0.0003

Data Index: 811893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0354. Min Act: -0.0003

Data Index: 171764 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0391. Min Act: -0.0003

Data Index: 811616 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0356. Min Act: -0.0003

Data Index: 690218 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1244002 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0361. Min Act: -0.0003

Data Index: 648105 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1270496 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0361. Min Act: -0.0003

Data Index: 602985 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0343. Min Act: -0.0003

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1308206 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0358. Min Act: -0.0003

Data Index: 837151 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0347. Min Act: -0.0003

Data Index: 1169541 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0350. Min Act: -0.0003

Data Index: 608400 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0344. Min Act: -0.0003

Data Index: 851027 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0345. Min Act: -0.0003

Data Index: 970114 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1171397 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0337. Min Act: -0.0003

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0349. Min Act: -0.0003

Data Index: 686540 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0335. Min Act: -0.0003

Data Index: 970183 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 0.0437. Min Range: -0.0437

Max Act: 0.0336. Min Act: -0.0003

Data Index: 896199 (C4 (Web Text))

Max Activating Token Index: 365