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

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

Neuron 60 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: 3.6806. Min Range: -3.6806

Max Act: 3.6711. Min Act: -0.0000

Data Index: 950319 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.6806. Min Act: -0.0000

Data Index: 1638985 (Python Code)

Max Activating Token Index: 662

Text #2

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.2302. Min Act: -0.0000

Data Index: 1240166 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.4297. Min Act: -0.0000

Data Index: 231899 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.3256. Min Act: -0.0000

Data Index: 442628 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1158. Min Act: -0.0000

Data Index: 1220816 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1342. Min Act: -0.0000

Data Index: 221918 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1480. Min Act: -0.0000

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.4338. Min Act: -0.0000

Data Index: 1087826 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8839. Min Act: -0.0000

Data Index: 840582 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8676. Min Act: -0.0000

Data Index: 858010 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8588. Min Act: -0.0000

Data Index: 89252 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.1135. Min Act: -0.0000

Data Index: 1185990 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.7532. Min Act: -0.0000

Data Index: 524346 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.8366. Min Act: -0.0000

Data Index: 664327 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.6400. Min Act: -0.0000

Data Index: 372412 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.6401. Min Act: -0.0000

Data Index: 797704 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.7530. Min Act: -0.0000

Data Index: 1113294 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 3.6806. Min Range: -3.6806

Max Act: 2.7208. Min Act: -0.0000

Data Index: 484206 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 3.6806. Min Range: -3.6806

Max Act: 3.0119. Min Act: -0.0000

Data Index: 1175040 (C4 (Web Text))

Max Activating Token Index: 954