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

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

Neuron 3032 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: 3.0407. Min Range: -3.0407

Max Act: 3.0407. Min Act: -0.0000

Data Index: 1057120 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.9115. Min Act: -0.0000

Data Index: 1202684 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.9190. Min Act: -0.0000

Data Index: 971203 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.4918. Min Act: -0.0000

Data Index: 1235848 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.4960. Min Act: -0.0000

Data Index: 408869 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.1446. Min Act: -0.0000

Data Index: 125298 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.5215. Min Act: -0.0000

Data Index: 608901 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.3931. Min Act: -0.0000

Data Index: 276979 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.3797. Min Act: -0.0000

Data Index: 513877 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.2973. Min Act: -0.0000

Data Index: 1095420 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.3576. Min Act: -0.0000

Data Index: 969320 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.2925. Min Act: -0.0000

Data Index: 654100 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.3171. Min Act: -0.0000

Data Index: 491333 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.3700. Min Act: -0.0000

Data Index: 189423 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.2513. Min Act: -0.0000

Data Index: 917073 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.2141. Min Act: -0.0000

Data Index: 671881 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 3.0407. Min Range: -3.0407

Max Act: 1.9921. Min Act: -0.0000

Data Index: 166453 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.1816. Min Act: -0.0000

Data Index: 298093 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.2105. Min Act: -0.0000

Data Index: 951887 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 3.0407. Min Range: -3.0407

Max Act: 2.0422. Min Act: -0.0000

Data Index: 1345460 (C4 (Web Text))

Max Activating Token Index: 877