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

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

Neuron 3800 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: 0.4198. Min Range: -0.4198

Max Act: 0.4198. Min Act: -0.0000

Data Index: 42058 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3734. Min Act: -0.0000

Data Index: 401656 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3017. Min Act: -0.0000

Data Index: 18583 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1269071 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3259. Min Act: -0.0000

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3178. Min Act: -0.0000

Data Index: 846948 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3042. Min Act: -0.0000

Data Index: 1303499 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2813. Min Act: -0.0000

Data Index: 301885 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2487. Min Act: -0.0000

Data Index: 873710 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2632. Min Act: -0.0000

Data Index: 504365 (C4 (Web Text))

Max Activating Token Index: 247

Text #10

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2652. Min Act: -0.0000

Data Index: 205078 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2456. Min Act: -0.0000

Data Index: 305482 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2513. Min Act: -0.0000

Data Index: 925629 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2499. Min Act: -0.0000

Data Index: 439425 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2309. Min Act: -0.0000

Data Index: 903778 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2194. Min Act: -0.0000

Data Index: 705562 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1029869 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2053. Min Act: -0.0000

Data Index: 332708 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.1959. Min Act: -0.0000

Data Index: 548705 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2247. Min Act: -0.0000

Data Index: 227753 (C4 (Web Text))

Max Activating Token Index: 498