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

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

Neuron 2070 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.2901. Min Act: -0.0000

Data Index: 93525 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.1594. Min Act: -0.0000

Data Index: 172355 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.2464. Min Act: -0.0000

Data Index: 1124731 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.1663. Min Act: -0.0000

Data Index: 615178 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.1917. Min Act: -0.0000

Data Index: 276075 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1222259 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.9468. Min Act: -0.0000

Data Index: 193526 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.1464. Min Act: -0.0000

Data Index: 941840 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 2.3089. Min Range: -2.3089

Max Act: 2.3089. Min Act: -0.0000

Data Index: 730327 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.7061. Min Act: -0.0000

Data Index: 666127 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.8853. Min Act: -0.0000

Data Index: 119434 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.9867. Min Act: -0.0000

Data Index: 570382 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.8118. Min Act: -0.0000

Data Index: 606350 (C4 (Web Text))

Max Activating Token Index: 155

Text #13

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.7783. Min Act: -0.0000

Data Index: 581692 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.8612. Min Act: -0.0000

Data Index: 1269033 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.6614. Min Act: -0.0000

Data Index: 1250046 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.7249. Min Act: -0.0000

Data Index: 2117 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1050190 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.6166. Min Act: -0.0000

Data Index: 889575 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 2.3089. Min Range: -2.3089

Max Act: 1.8122. Min Act: -0.0000

Data Index: 403850 (C4 (Web Text))

Max Activating Token Index: 737