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

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

Neuron 2 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4471. Min Act: -0.0000

Data Index: 501351 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4132. Min Act: -0.0000

Data Index: 678005 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.4512. Min Act: -0.0000

Data Index: 460077 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3897. Min Act: -0.0000

Data Index: 737366 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3492. Min Act: -0.0000

Data Index: 873184 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3134. Min Act: -0.0000

Data Index: 423515 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.3005. Min Act: -0.0000

Data Index: 694940 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2759. Min Act: -0.0000

Data Index: 405992 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2347. Min Act: -0.0000

Data Index: 959546 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2504. Min Act: -0.0000

Data Index: 403729 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2613. Min Act: -0.0000

Data Index: 776978 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2454. Min Act: -0.0000

Data Index: 41817 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2294. Min Act: -0.0000

Data Index: 757730 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2566. Min Act: -0.0000

Data Index: 494942 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2300. Min Act: -0.0000

Data Index: 464012 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2358. Min Act: -0.0000

Data Index: 114677 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2222. Min Act: -0.0000

Data Index: 852251 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2296. Min Act: -0.0000

Data Index: 846356 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2285. Min Act: -0.0000

Data Index: 366360 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.4512. Min Range: -0.4512

Max Act: 0.2447. Min Act: -0.0000

Data Index: 1266146 (C4 (Web Text))

Max Activating Token Index: 761