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

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

Neuron 3234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3291. Min Act: -0.0002

Data Index: 857996 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3256. Min Act: -0.0002

Data Index: 762161 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3224. Min Act: -0.0002

Data Index: 410050 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3224. Min Act: -0.0002

Data Index: 1175689 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3224. Min Act: -0.0002

Data Index: 439032 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3092. Min Act: -0.0002

Data Index: 479910 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2750. Min Act: -0.0002

Data Index: 287517 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2869. Min Act: -0.0002

Data Index: 175418 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2889. Min Act: -0.0002

Data Index: 979153 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2826. Min Act: -0.0002

Data Index: 1051750 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.3074. Min Act: -0.0002

Data Index: 369205 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2821. Min Act: -0.0002

Data Index: 768107 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2733. Min Act: -0.0002

Data Index: 486207 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2807. Min Act: -0.0002

Data Index: 747562 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2690. Min Act: -0.0002

Data Index: 793216 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2842. Min Act: -0.0002

Data Index: 258675 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2731. Min Act: -0.0002

Data Index: 376714 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2461. Min Act: -0.0002

Data Index: 214659 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2677. Min Act: -0.0002

Data Index: 1149454 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 0.3291. Min Range: -0.3291

Max Act: 0.2681. Min Act: -0.0002

Data Index: 1309502 (C4 (Web Text))

Max Activating Token Index: 484