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

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

Neuron 140 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4981. Min Range: -5.4981

Max Act: 5.4981. Min Act: -0.0000

Data Index: 575541 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 5.4981. Min Range: -5.4981

Max Act: 5.3102. Min Act: -0.0000

Data Index: 832908 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.8524. Min Act: -0.0000

Data Index: 1051702 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.8589. Min Act: -0.0000

Data Index: 323995 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.5033. Min Act: -0.0000

Data Index: 610717 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.4192. Min Act: -0.0000

Data Index: 219021 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.5446. Min Act: -0.0000

Data Index: 1066946 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.1959. Min Act: -0.0000

Data Index: 125534 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.6764. Min Act: -0.0000

Data Index: 520119 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.4627. Min Act: -0.0000

Data Index: 189440 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.8134. Min Act: -0.0000

Data Index: 1230852 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.6401. Min Act: -0.0000

Data Index: 1334206 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.3407. Min Act: -0.0000

Data Index: 119088 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.5632. Min Act: -0.0000

Data Index: 1207335 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.3636. Min Act: -0.0000

Data Index: 387653 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.3639. Min Act: -0.0000

Data Index: 114095 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.1704. Min Act: -0.0000

Data Index: 819410 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.3203. Min Act: -0.0000

Data Index: 721919 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.1433. Min Act: -0.0000

Data Index: 859339 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 5.4981. Min Range: -5.4981

Max Act: 4.4987. Min Act: -0.0000

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 166