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

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

Neuron 2166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4405. Min Act: -0.0000

Data Index: 956268 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4480. Min Act: -0.0000

Data Index: 174994 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1176362 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3961. Min Act: -0.0000

Data Index: 509279 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4219. Min Act: -0.0000

Data Index: 974576 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4167. Min Act: -0.0000

Data Index: 201506 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3917. Min Act: -0.0000

Data Index: 424578 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1183335 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1018410 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1229384 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4227. Min Act: -0.0000

Data Index: 227213 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3834. Min Act: -0.0000

Data Index: 966146 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1065569 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.4120. Min Act: -0.0000

Data Index: 403614 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3825. Min Act: -0.0000

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3745. Min Act: -0.0000

Data Index: 107320 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1234378 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3888. Min Act: -0.0000

Data Index: 924192 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1251067 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.4480. Min Range: -0.4480

Max Act: 0.3939. Min Act: -0.0000

Data Index: 913349 (C4 (Web Text))

Max Activating Token Index: 785