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

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

Neuron 117 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: 0.5587. Min Range: -0.5587

Max Act: 0.5363. Min Act: 0.0001

Data Index: 667219 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.5587. Min Act: -0.0000

Data Index: 654119 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4955. Min Act: -0.0000

Data Index: 960259 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4530. Min Act: -0.0000

Data Index: 859294 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4734. Min Act: -0.0000

Data Index: 229861 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4396. Min Act: 0.0001

Data Index: 1111958 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4110. Min Act: -0.0000

Data Index: 734695 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3949. Min Act: -0.0000

Data Index: 340051 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4174. Min Act: 0.0000

Data Index: 640065 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4119. Min Act: -0.0000

Data Index: 215120 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4145. Min Act: -0.0000

Data Index: 158063 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4208. Min Act: -0.0000

Data Index: 246187 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1198352 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4079. Min Act: -0.0000

Data Index: 126685 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4234. Min Act: 0.0000

Data Index: 1283594 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4347. Min Act: 0.0001

Data Index: 640180 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3977. Min Act: -0.0000

Data Index: 355110 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4015. Min Act: -0.0000

Data Index: 1085561 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.4005. Min Act: -0.0000

Data Index: 966753 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.5587. Min Range: -0.5587

Max Act: 0.3980. Min Act: -0.0000

Data Index: 522366 (C4 (Web Text))

Max Activating Token Index: 485