Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2278 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0002. Min Range: -1.0002

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1260022 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.9677. Min Act: -0.0001

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.9365. Min Act: -0.0001

Data Index: 160520 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.9115. Min Act: -0.0001

Data Index: 1117552 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8211. Min Act: -0.0001

Data Index: 225356 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7915. Min Act: -0.0001

Data Index: 23345 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8665. Min Act: -0.0001

Data Index: 461200 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8526. Min Act: -0.0001

Data Index: 963134 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8105. Min Act: -0.0001

Data Index: 828840 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8482. Min Act: -0.0001

Data Index: 341876 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7796. Min Act: -0.0001

Data Index: 725384 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8286. Min Act: -0.0001

Data Index: 809005 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7999. Min Act: -0.0001

Data Index: 1204265 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7966. Min Act: -0.0001

Data Index: 681207 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1284448 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7653. Min Act: -0.0001

Data Index: 169260 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.8072. Min Act: -0.0001

Data Index: 473290 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7073. Min Act: -0.0001

Data Index: 995637 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7890. Min Act: -0.0001

Data Index: 793923 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.0002. Min Range: -1.0002

Max Act: 0.7330. Min Act: -0.0001

Data Index: 1325755 (C4 (Web Text))

Max Activating Token Index: 217