Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4540. Min Range: -4.4540

Max Act: 4.1663. Min Act: -0.0000

Data Index: 286658 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 4.4540. Min Range: -4.4540

Max Act: 4.1575. Min Act: -0.0000

Data Index: 1180864 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.5805. Min Act: -0.0000

Data Index: 1331320 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.9404. Min Act: -0.0000

Data Index: 1072254 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 4.4540. Min Range: -4.4540

Max Act: 4.4340. Min Act: -0.0000

Data Index: 971433 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.9944. Min Act: -0.0000

Data Index: 435282 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 4.4540. Min Range: -4.4540

Max Act: 4.4540. Min Act: -0.0000

Data Index: 8138 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.8344. Min Act: -0.0000

Data Index: 918911 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.8511. Min Act: -0.0000

Data Index: 870704 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.7977. Min Act: -0.0000

Data Index: 891459 (C4 (Web Text))

Max Activating Token Index: 1017

Text #10

Max Range: 4.4540. Min Range: -4.4540

Max Act: 4.0694. Min Act: -0.0000

Data Index: 1031629 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.5246. Min Act: -0.0000

Data Index: 1343100 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.9468. Min Act: -0.0000

Data Index: 631555 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.6147. Min Act: -0.0000

Data Index: 259742 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.4536. Min Act: -0.0000

Data Index: 1326886 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.2413. Min Act: -0.0001

Data Index: 478269 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.2576. Min Act: -0.0000

Data Index: 494550 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.0724. Min Act: -0.0000

Data Index: 1221341 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.3314. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 1005

Text #19

Max Range: 4.4540. Min Range: -4.4540

Max Act: 3.1444. Min Act: -0.0000

Data Index: 1272488 (C4 (Web Text))

Max Activating Token Index: 890