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

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

Neuron 1705 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.4263. Min Act: -0.0001

Data Index: 456547 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3635. Min Act: -0.0001

Data Index: 949916 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3419. Min Act: -0.0001

Data Index: 967145 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3572. Min Act: -0.0001

Data Index: 392956 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3396. Min Act: -0.0001

Data Index: 773048 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3501. Min Act: -0.0001

Data Index: 52954 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3264. Min Act: -0.0001

Data Index: 8903 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1204034 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3463. Min Act: -0.0001

Data Index: 975392 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3246. Min Act: -0.0001

Data Index: 622868 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3184. Min Act: -0.0001

Data Index: 651578 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3062. Min Act: -0.0001

Data Index: 38089 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1025890 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3147. Min Act: -0.0001

Data Index: 884558 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3248. Min Act: -0.0001

Data Index: 455321 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3347. Min Act: -0.0001

Data Index: 203999 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1257851 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3182. Min Act: -0.0001

Data Index: 964858 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3331. Min Act: -0.0001

Data Index: 452712 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.4263. Min Range: -0.4263

Max Act: 0.3426. Min Act: -0.0001

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 867