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

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

Neuron 5003 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2490. Min Range: -4.2490

Max Act: 4.2490. Min Act: -0.0000

Data Index: 1295024 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.9294. Min Act: -0.0000

Data Index: 35354 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.5402. Min Act: -0.0000

Data Index: 412314 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.3585. Min Act: -0.0000

Data Index: 735084 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.1765. Min Act: -0.0000

Data Index: 873562 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.3993. Min Act: -0.0000

Data Index: 886460 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.0632. Min Act: -0.0000

Data Index: 543152 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.3396. Min Act: -0.0000

Data Index: 113166 (C4 (Web Text))

Max Activating Token Index: 884

Text #8

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9986. Min Act: -0.0000

Data Index: 55844 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.3956. Min Act: -0.0000

Data Index: 1033347 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.0784. Min Act: -0.0000

Data Index: 519435 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.2180. Min Act: -0.0000

Data Index: 549280 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.0388. Min Act: -0.0000

Data Index: 115260 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.7816. Min Act: -0.0000

Data Index: 569604 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 4.2490. Min Range: -4.2490

Max Act: 3.0279. Min Act: -0.0000

Data Index: 350163 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9894. Min Act: -0.0000

Data Index: 408378 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9594. Min Act: -0.0000

Data Index: 1193516 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9707. Min Act: -0.0000

Data Index: 548786 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9294. Min Act: -0.0000

Data Index: 29455 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 4.2490. Min Range: -4.2490

Max Act: 2.9349. Min Act: -0.0000

Data Index: 790738 (C4 (Web Text))

Max Activating Token Index: 1016