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

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

Neuron 1078 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: 2.1493. Min Range: -2.1493

Max Act: 2.1390. Min Act: -0.0000

Data Index: 332615 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 2.1493. Min Range: -2.1493

Max Act: 2.1493. Min Act: -0.0000

Data Index: 1287960 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 2.1493. Min Range: -2.1493

Max Act: 2.1125. Min Act: -0.0000

Data Index: 612934 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1327066 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.9316. Min Act: -0.0000

Data Index: 136153 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.9000. Min Act: -0.0000

Data Index: 394317 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.6825. Min Act: -0.0000

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.4682. Min Act: -0.0000

Data Index: 272804 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.7363. Min Act: -0.0000

Data Index: 721475 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.6852. Min Act: -0.0000

Data Index: 663144 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1318665 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.5407. Min Act: -0.0000

Data Index: 410051 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.6893. Min Act: -0.0000

Data Index: 13386 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.4773. Min Act: -0.0000

Data Index: 1027472 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.5897. Min Act: -0.0000

Data Index: 307771 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.5550. Min Act: -0.0000

Data Index: 351060 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.4641. Min Act: -0.0000

Data Index: 520868 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.5352. Min Act: -0.0000

Data Index: 368347 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.5392. Min Act: -0.0000

Data Index: 1211270 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 2.1493. Min Range: -2.1493

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1345284 (C4 (Web Text))

Max Activating Token Index: 225