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

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

Neuron 377 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: 1.7486. Min Range: -1.7486

Max Act: 1.7486. Min Act: -0.0001

Data Index: 891489 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5748. Min Act: -0.0000

Data Index: 1346002 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5492. Min Act: -0.0001

Data Index: 867076 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5581. Min Act: -0.0000

Data Index: 539677 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4947. Min Act: -0.0000

Data Index: 557774 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.5381. Min Act: -0.0000

Data Index: 935389 (C4 (Web Text))

Max Activating Token Index: 225

Text #6

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4576. Min Act: -0.0000

Data Index: 1339676 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3232. Min Act: -0.0000

Data Index: 725117 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3061. Min Act: -0.0001

Data Index: 8152 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2377. Min Act: -0.0000

Data Index: 59998 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2796. Min Act: -0.0000

Data Index: 651704 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2174. Min Act: -0.0000

Data Index: 411676 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1653. Min Act: -0.0000

Data Index: 324611 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1497. Min Act: -0.0000

Data Index: 573982 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2148. Min Act: -0.0000

Data Index: 436284 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1313. Min Act: -0.0000

Data Index: 715460 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1471. Min Act: -0.0001

Data Index: 165130 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1126. Min Act: -0.0000

Data Index: 63502 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1015388 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1312753 (C4 (Web Text))

Max Activating Token Index: 158