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

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

Neuron 2353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.5084. Min Act: -0.0002

Data Index: 1336510 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4506. Min Act: -0.0002

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4904. Min Act: -0.0002

Data Index: 924736 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4883. Min Act: -0.0002

Data Index: 777256 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4099. Min Act: -0.0002

Data Index: 963149 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4365. Min Act: -0.0002

Data Index: 66301 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4652. Min Act: -0.0002

Data Index: 772789 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4947. Min Act: -0.0002

Data Index: 996930 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4231. Min Act: -0.0002

Data Index: 147875 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4740. Min Act: -0.0002

Data Index: 1002794 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4726. Min Act: -0.0002

Data Index: 990555 (C4 (Web Text))

Max Activating Token Index: 726

Text #11

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4375. Min Act: -0.0002

Data Index: 29707 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4823. Min Act: -0.0002

Data Index: 686373 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4477. Min Act: -0.0002

Data Index: 1289774 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4619. Min Act: -0.0002

Data Index: 235601 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4479. Min Act: -0.0002

Data Index: 224277 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4663. Min Act: -0.0002

Data Index: 269520 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.3871. Min Act: -0.0002

Data Index: 22407 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4436. Min Act: -0.0002

Data Index: 87729 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.5084. Min Range: -0.5084

Max Act: 0.4369. Min Act: -0.0002

Data Index: 995127 (C4 (Web Text))

Max Activating Token Index: 135