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

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

Neuron 2108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.5392. Min Act: -0.0001

Data Index: 919440 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.4595. Min Act: -0.0001

Data Index: 906458 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.5096. Min Act: -0.0000

Data Index: 742959 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3540. Min Act: -0.0001

Data Index: 1098027 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.4321. Min Act: -0.0000

Data Index: 873353 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3373. Min Act: -0.0000

Data Index: 565343 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3135. Min Act: -0.0000

Data Index: 353863 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3511. Min Act: -0.0000

Data Index: 739464 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3785. Min Act: -0.0000

Data Index: 1315553 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3064. Min Act: -0.0001

Data Index: 171904 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2974. Min Act: -0.0001

Data Index: 1086736 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2450. Min Act: -0.0000

Data Index: 300084 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2763. Min Act: -0.0001

Data Index: 1044741 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.3092. Min Act: -0.0000

Data Index: 1128246 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2029. Min Act: -0.0001

Data Index: 857249 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1117089 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2400. Min Act: -0.0000

Data Index: 117467 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2098. Min Act: -0.0000

Data Index: 1168823 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2309. Min Act: -0.0000

Data Index: 223257 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 1.5392. Min Range: -1.5392

Max Act: 1.2410. Min Act: -0.0001

Data Index: 771908 (C4 (Web Text))

Max Activating Token Index: 219