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

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

Neuron 572 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: 1.5548. Min Range: -1.5548

Max Act: 1.5548. Min Act: -0.0001

Data Index: 953702 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.4004. Min Act: -0.0001

Data Index: 1045546 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.3433. Min Act: -0.0001

Data Index: 1284031 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.2357. Min Act: -0.0001

Data Index: 1358677 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.2073. Min Act: -0.0001

Data Index: 126414 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.3036. Min Act: -0.0001

Data Index: 127311 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.2190. Min Act: -0.0001

Data Index: 1349958 (C4 (Web Text))

Max Activating Token Index: 935

Text #7

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1914. Min Act: -0.0001

Data Index: 272595 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1648. Min Act: -0.0001

Data Index: 1216790 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0071. Min Act: -0.0001

Data Index: 1095916 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0452. Min Act: -0.0001

Data Index: 58203 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1101. Min Act: -0.0001

Data Index: 637819 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0682. Min Act: -0.0001

Data Index: 956777 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0047. Min Act: -0.0001

Data Index: 599858 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.1309. Min Act: -0.0001

Data Index: 140211 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0309. Min Act: -0.0001

Data Index: 158507 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0536. Min Act: -0.0001

Data Index: 109395 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0190. Min Act: -0.0001

Data Index: 258165 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0402. Min Act: -0.0001

Data Index: 898119 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.5548. Min Range: -1.5548

Max Act: 1.0018. Min Act: -0.0001

Data Index: 945256 (C4 (Web Text))

Max Activating Token Index: 1017