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

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

Neuron 3707 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.5272. Min Act: -0.0001

Data Index: 723377 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.4066. Min Act: -0.0001

Data Index: 877725 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.4418. Min Act: -0.0001

Data Index: 39529 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.3646. Min Act: -0.0001

Data Index: 895524 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.4273. Min Act: -0.0001

Data Index: 1135292 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2914. Min Act: -0.0001

Data Index: 565782 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2194. Min Act: -0.0001

Data Index: 260066 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2647. Min Act: -0.0001

Data Index: 920533 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1848. Min Act: -0.0001

Data Index: 544385 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.2077. Min Act: -0.0001

Data Index: 519159 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1644. Min Act: -0.0001

Data Index: 1091715 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1084883 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1104. Min Act: -0.0001

Data Index: 190999 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.1321. Min Act: -0.0001

Data Index: 1013309 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1007985 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0315. Min Act: -0.0001

Data Index: 1067233 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0583. Min Act: -0.0001

Data Index: 187577 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0444. Min Act: -0.0001

Data Index: 1331541 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0687. Min Act: -0.0001

Data Index: 546065 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.5272. Min Range: -1.5272

Max Act: 1.0266. Min Act: -0.0001

Data Index: 795425 (C4 (Web Text))

Max Activating Token Index: 728