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

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

Neuron 330 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0001

Data Index: 34233 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1259319 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0820. Min Act: -0.0001

Data Index: 1009834 (C4 (Web Text))

Max Activating Token Index: 387

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0821. Min Act: -0.0001

Data Index: 680950 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0826. Min Act: -0.0001

Data Index: 361240 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0823. Min Act: -0.0001

Data Index: 161901 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0699. Min Act: -0.0001

Data Index: 108952 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0723. Min Act: -0.0001

Data Index: 422514 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0766. Min Act: -0.0001

Data Index: 112830 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1230363 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0686. Min Act: -0.0001

Data Index: 211502 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1089249 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0687. Min Act: -0.0001

Data Index: 240702 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1103098 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0746. Min Act: -0.0001

Data Index: 230263 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0678. Min Act: -0.0001

Data Index: 432822 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0706. Min Act: -0.0001

Data Index: 757532 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0708. Min Act: -0.0001

Data Index: 45684 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0707. Min Act: -0.0001

Data Index: 337353 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0737. Min Act: -0.0001

Data Index: 117151 (C4 (Web Text))

Max Activating Token Index: 370