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

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

Neuron 5182 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.8466. Min Act: -0.0000

Data Index: 1164952 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.5512. Min Act: -0.0000

Data Index: 825165 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.4965. Min Act: -0.0000

Data Index: 217479 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.4204. Min Act: -0.0000

Data Index: 150096 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.3692. Min Act: -0.0000

Data Index: 208716 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.3372. Min Act: -0.0000

Data Index: 631494 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.1412. Min Act: -0.0000

Data Index: 1198734 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.4893. Min Act: -0.0000

Data Index: 1105010 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.4764. Min Act: -0.0000

Data Index: 1264336 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.2756. Min Act: -0.0000

Data Index: 884638 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.4437. Min Act: -0.0000

Data Index: 721402 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.0775. Min Act: -0.0000

Data Index: 621114 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.2193. Min Act: -0.0000

Data Index: 926248 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.5478. Min Act: -0.0000

Data Index: 805093 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.1923. Min Act: -0.0000

Data Index: 391988 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.0002. Min Act: -0.0000

Data Index: 921258 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.1674. Min Act: -0.0000

Data Index: 1102577 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.1700. Min Act: -0.0000

Data Index: 908702 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.1661. Min Act: -0.0000

Data Index: 130379 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.0002. Min Act: -0.0000

Data Index: 257867 (C4 (Web Text))

Max Activating Token Index: 363