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

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

Neuron 2963 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2985. Min Range: -4.2985

Max Act: 4.2985. Min Act: -0.0000

Data Index: 1087096 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 4.2985. Min Range: -4.2985

Max Act: 4.0076. Min Act: -0.0000

Data Index: 839 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.9522. Min Act: -0.0000

Data Index: 631990 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.5584. Min Act: -0.0000

Data Index: 1078643 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.5011. Min Act: -0.0000

Data Index: 931277 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.3819. Min Act: -0.0000

Data Index: 1062268 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.2649. Min Act: -0.0000

Data Index: 891709 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.2598. Min Act: -0.0000

Data Index: 860133 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.2355. Min Act: -0.0000

Data Index: 917391 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.9935. Min Act: -0.0000

Data Index: 243594 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.1381. Min Act: -0.0000

Data Index: 1169502 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.1246. Min Act: -0.0000

Data Index: 463846 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 4.2985. Min Range: -4.2985

Max Act: 3.0372. Min Act: -0.0000

Data Index: 545647 (C4 (Web Text))

Max Activating Token Index: 124

Text #13

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.8744. Min Act: -0.0000

Data Index: 568246 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.9729. Min Act: -0.0000

Data Index: 735807 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.8266. Min Act: -0.0000

Data Index: 1461194 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.9160. Min Act: -0.0000

Data Index: 455350 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.7208. Min Act: -0.0000

Data Index: 948662 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.6778. Min Act: -0.0000

Data Index: 1193903 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 4.2985. Min Range: -4.2985

Max Act: 2.6196. Min Act: -0.0000

Data Index: 512482 (C4 (Web Text))

Max Activating Token Index: 784