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

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

Neuron 2975 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: 5.4758. Min Range: -5.4758

Max Act: 5.4758. Min Act: -0.0000

Data Index: 1024917 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.0578. Min Act: -0.0000

Data Index: 376205 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.8390. Min Act: -0.0000

Data Index: 399406 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9797. Min Act: -0.0000

Data Index: 1033217 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9451. Min Act: -0.0000

Data Index: 44943 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.5902. Min Act: -0.0000

Data Index: 902380 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.5584. Min Act: -0.0000

Data Index: 837244 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.3889. Min Act: -0.0000

Data Index: 416658 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.3522. Min Act: -0.0000

Data Index: 741394 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.3647. Min Act: -0.0000

Data Index: 1226736 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.1767. Min Act: -0.0000

Data Index: 1205932 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.2992. Min Act: -0.0000

Data Index: 1141031 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.2007. Min Act: -0.0000

Data Index: 1070083 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.0328. Min Act: -0.0000

Data Index: 182317 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.0103. Min Act: -0.0000

Data Index: 1195873 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.1625. Min Act: -0.0000

Data Index: 1263021 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.1154. Min Act: -0.0000

Data Index: 1197902 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.1051. Min Act: -0.0000

Data Index: 248448 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 5.4758. Min Range: -5.4758

Max Act: 2.9176. Min Act: -0.0000

Data Index: 513287 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.0603. Min Act: -0.0000

Data Index: 899398 (C4 (Web Text))

Max Activating Token Index: 467