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

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

Neuron 4793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1303891 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7858. Min Act: -0.0000

Data Index: 126527 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1261676 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1322850 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1173701 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1022550 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5992. Min Act: -0.0000

Data Index: 787742 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6189. Min Act: -0.0000

Data Index: 642963 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6223. Min Act: -0.0000

Data Index: 503085 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5150. Min Act: -0.0000

Data Index: 378628 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5143. Min Act: -0.0000

Data Index: 455571 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1159746 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1315557 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5092. Min Act: -0.0000

Data Index: 729775 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5111. Min Act: -0.0000

Data Index: 862839 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5235. Min Act: -0.0000

Data Index: 267275 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.4893. Min Act: -0.0000

Data Index: 736828 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.4891. Min Act: -0.0000

Data Index: 288730 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1123523 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.4670. Min Act: -0.0000

Data Index: 2489 (C4 (Web Text))

Max Activating Token Index: 267