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

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

Neuron 3101 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0684. Min Range: -2.0684

Max Act: 2.0684. Min Act: -0.0000

Data Index: 458563 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.8593. Min Act: -0.0000

Data Index: 645590 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.7755. Min Act: -0.0000

Data Index: 279124 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.7816. Min Act: -0.0000

Data Index: 269222 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.7132. Min Act: -0.0000

Data Index: 975386 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.7196. Min Act: -0.0000

Data Index: 1066533 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.6832. Min Act: -0.0000

Data Index: 461202 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.6766. Min Act: -0.0000

Data Index: 180997 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4683. Min Act: -0.0000

Data Index: 808442 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4906. Min Act: -0.0000

Data Index: 362084 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4937. Min Act: -0.0000

Data Index: 1159146 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4469. Min Act: -0.0000

Data Index: 60339 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.5153. Min Act: -0.0000

Data Index: 72964 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.5434. Min Act: -0.0000

Data Index: 1171217 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4349. Min Act: -0.0000

Data Index: 439732 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1339815 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4436. Min Act: -0.0000

Data Index: 96349 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.5954. Min Act: -0.0000

Data Index: 395354 (C4 (Web Text))

Max Activating Token Index: 434

Text #18

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.5598. Min Act: -0.0000

Data Index: 417836 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 2.0684. Min Range: -2.0684

Max Act: 1.4768. Min Act: -0.0000

Data Index: 867970 (C4 (Web Text))

Max Activating Token Index: 830