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

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

Neuron 311 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: 2.4273. Min Range: -2.4273

Max Act: 2.4273. Min Act: -0.0000

Data Index: 1073788 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.2885. Min Act: -0.0000

Data Index: 1054462 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.2864. Min Act: -0.0000

Data Index: 565976 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1838. Min Act: -0.0000

Data Index: 1191759 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1809. Min Act: -0.0000

Data Index: 1325647 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1005. Min Act: -0.0000

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1499. Min Act: -0.0000

Data Index: 996929 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1337. Min Act: -0.0000

Data Index: 470452 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1204. Min Act: -0.0000

Data Index: 786122 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1086. Min Act: -0.0000

Data Index: 820667 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1694. Min Act: -0.0000

Data Index: 818940 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 2.4273. Min Range: -2.4273

Max Act: 1.9602. Min Act: -0.0000

Data Index: 1027434 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1119. Min Act: -0.0000

Data Index: 650555 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.0408. Min Act: -0.0000

Data Index: 650238 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.4273. Min Range: -2.4273

Max Act: 1.9536. Min Act: -0.0000

Data Index: 759706 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.0542. Min Act: -0.0000

Data Index: 270405 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 2.4273. Min Range: -2.4273

Max Act: 2.1046. Min Act: -0.0000

Data Index: 806126 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 2.4273. Min Range: -2.4273

Max Act: 1.9537. Min Act: -0.0000

Data Index: 1098903 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 2.4273. Min Range: -2.4273

Max Act: 1.8547. Min Act: -0.0000

Data Index: 15029 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.4273. Min Range: -2.4273

Max Act: 1.8315. Min Act: -0.0000

Data Index: 652192 (C4 (Web Text))

Max Activating Token Index: 748