Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 878 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0006

Data Index: 719248 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0209. Min Act: -0.0006

Data Index: 12605 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0204. Min Act: -0.0006

Data Index: 123833 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0208. Min Act: -0.0006

Data Index: 922716 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0208. Min Act: -0.0006

Data Index: 353802 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0206. Min Act: -0.0007

Data Index: 801643 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0205. Min Act: -0.0006

Data Index: 467152 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1017647 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0199. Min Act: -0.0006

Data Index: 223655 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0197. Min Act: -0.0006

Data Index: 534822 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0202. Min Act: -0.0006

Data Index: 822146 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0192. Min Act: -0.0006

Data Index: 642908 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1027036 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0200. Min Act: -0.0006

Data Index: 1226290 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1273675 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0204. Min Act: -0.0006

Data Index: 480894 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0199. Min Act: -0.0006

Data Index: 562263 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0193. Min Act: -0.0006

Data Index: 858022 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0198. Min Act: -0.0006

Data Index: 1337173 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0201. Min Act: -0.0006

Data Index: 1296636 (C4 (Web Text))

Max Activating Token Index: 73