Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4693 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.4799. Min Act: -0.0000

Data Index: 672784 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.3701. Min Act: -0.0000

Data Index: 791793 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1571. Min Act: -0.0000

Data Index: 408106 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.2488. Min Act: -0.0000

Data Index: 992909 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1775. Min Act: -0.0000

Data Index: 973968 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1363. Min Act: -0.0000

Data Index: 490643 (C4 (Web Text))

Max Activating Token Index: 678

Text #6

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1776. Min Act: -0.0000

Data Index: 1301762 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1708. Min Act: -0.0000

Data Index: 1009736 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1588. Min Act: -0.0000

Data Index: 1325570 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1111. Min Act: -0.0000

Data Index: 1009194 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.0814. Min Act: -0.0000

Data Index: 1164263 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.0340. Min Act: -0.0000

Data Index: 494048 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.0246. Min Act: -0.0000

Data Index: 24239 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.0022. Min Act: -0.0000

Data Index: 826674 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.1418. Min Act: -0.0000

Data Index: 473543 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 1.4799. Min Range: -1.4799

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1356896 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.4799. Min Range: -1.4799

Max Act: 0.9235. Min Act: -0.0000

Data Index: 869392 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.4799. Min Range: -1.4799

Max Act: 1.0955. Min Act: -0.0000

Data Index: 281819 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.4799. Min Range: -1.4799

Max Act: 0.9280. Min Act: -0.0000

Data Index: 188711 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.4799. Min Range: -1.4799

Max Act: 0.9046. Min Act: -0.0000

Data Index: 355093 (C4 (Web Text))

Max Activating Token Index: 706