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

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

Neuron 4124 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2745. Min Range: -2.2745

Max Act: 2.2745. Min Act: -0.0000

Data Index: 966647 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.8118. Min Act: -0.0000

Data Index: 44824 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 2.2745. Min Range: -2.2745

Max Act: 2.0992. Min Act: -0.0000

Data Index: 1092456 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.9533. Min Act: -0.0000

Data Index: 737381 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.9670. Min Act: -0.0001

Data Index: 1179079 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.9114. Min Act: -0.0000

Data Index: 766214 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.8447. Min Act: -0.0000

Data Index: 654400 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.6808. Min Act: -0.0000

Data Index: 1181517 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.9443. Min Act: -0.0000

Data Index: 476302 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.8382. Min Act: -0.0000

Data Index: 1026092 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.7300. Min Act: -0.0000

Data Index: 998518 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.8051. Min Act: -0.0000

Data Index: 460685 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.6931. Min Act: -0.0000

Data Index: 592645 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.7849. Min Act: -0.0000

Data Index: 253823 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.7657. Min Act: -0.0000

Data Index: 339181 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.6696. Min Act: -0.0000

Data Index: 215651 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.7597. Min Act: -0.0000

Data Index: 660862 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.6319. Min Act: -0.0000

Data Index: 1297959 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.6484. Min Act: -0.0000

Data Index: 513795 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.2745. Min Range: -2.2745

Max Act: 1.7234. Min Act: -0.0000

Data Index: 932625 (C4 (Web Text))

Max Activating Token Index: 25