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

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

Neuron 4165 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.8042. Min Act: -0.0000

Data Index: 92495 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.5422. Min Act: -0.0000

Data Index: 70336 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.5292. Min Act: -0.0000

Data Index: 422891 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.5084. Min Act: -0.0000

Data Index: 924508 (C4 (Web Text))

Max Activating Token Index: 1020

Text #4

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.5040. Min Act: -0.0000

Data Index: 358818 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.5000. Min Act: -0.0000

Data Index: 612921 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4939. Min Act: -0.0000

Data Index: 421499 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4733. Min Act: -0.0000

Data Index: 943686 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1038048 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4573. Min Act: -0.0000

Data Index: 216966 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4424. Min Act: -0.0000

Data Index: 297617 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4537. Min Act: -0.0000

Data Index: 369045 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1023501 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4329. Min Act: -0.0000

Data Index: 588729 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4128. Min Act: -0.0000

Data Index: 763440 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4108. Min Act: 0.0000

Data Index: 1143423 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.4073. Min Act: -0.0000

Data Index: 390008 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1306561 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1330591 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.8042. Min Range: -0.8042

Max Act: 0.3834. Min Act: -0.0000

Data Index: 29180 (C4 (Web Text))

Max Activating Token Index: 234