Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1225 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2806. Min Range: -1.2806

Max Act: 1.2806. Min Act: -0.0000

Data Index: 1606740 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1260026 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1419763 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1588081 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1208510 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1582241 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5496. Min Act: -0.0000

Data Index: 303386 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1147842 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5487. Min Act: -0.0000

Data Index: 493024 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5372. Min Act: -0.0000

Data Index: 312974 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1266447 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4731. Min Act: -0.0000

Data Index: 410563 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5179. Min Act: -0.0000

Data Index: 80731 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4762. Min Act: -0.0000

Data Index: 570228 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1249499 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4884. Min Act: -0.0000

Data Index: 314035 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4843. Min Act: -0.0000

Data Index: 746692 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1161585 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.5165. Min Act: -0.0000

Data Index: 603299 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.2806. Min Range: -1.2806

Max Act: 0.4528. Min Act: -0.0000

Data Index: 811141 (C4 (Web Text))

Max Activating Token Index: 864