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

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

Neuron 481 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0765. Min Act: -0.0000

Data Index: 194159 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0604. Min Act: -0.0000

Data Index: 311075 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1259132 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.1172. Min Act: -0.0000

Data Index: 206324 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0083. Min Act: -0.0000

Data Index: 900293 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0187. Min Act: -0.0000

Data Index: 170962 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0134. Min Act: -0.0000

Data Index: 513599 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9663. Min Act: -0.0000

Data Index: 276380 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0302. Min Act: -0.0000

Data Index: 660886 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9827. Min Act: -0.0000

Data Index: 896947 (C4 (Web Text))

Max Activating Token Index: 275

Text #10

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1358173 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 1.1172. Min Range: -1.1172

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1324478 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9979. Min Act: -0.0000

Data Index: 194048 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9528. Min Act: -0.0000

Data Index: 523905 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9734. Min Act: -0.0000

Data Index: 77986 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1288903 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1227945 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9643. Min Act: -0.0000

Data Index: 58054 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9469. Min Act: -0.0000

Data Index: 525367 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 1.1172. Min Range: -1.1172

Max Act: 0.9165. Min Act: -0.0000

Data Index: 996327 (C4 (Web Text))

Max Activating Token Index: 957