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

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

Neuron 3755 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.6433. Min Act: -0.0000

Data Index: 14049 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.6243. Min Act: -0.0000

Data Index: 584447 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.5898. Min Act: -0.0000

Data Index: 841149 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4971. Min Act: -0.0000

Data Index: 692329 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4857. Min Act: -0.0000

Data Index: 588123 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.7459. Min Act: -0.0000

Data Index: 1399 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.3590. Min Act: -0.0000

Data Index: 95846 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4918. Min Act: -0.0000

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.2780. Min Act: -0.0000

Data Index: 99336 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4009. Min Act: -0.0000

Data Index: 1113544 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.2792. Min Act: -0.0000

Data Index: 767558 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.2715. Min Act: -0.0000

Data Index: 1334877 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.3888. Min Act: -0.0000

Data Index: 841629 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.3813. Min Act: -0.0000

Data Index: 1082554 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.5029. Min Act: -0.0000

Data Index: 9180 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4946. Min Act: -0.0000

Data Index: 109309 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.4930. Min Act: -0.0000

Data Index: 1324686 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.2416. Min Act: -0.0000

Data Index: 856938 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.2446. Min Act: -0.0000

Data Index: 640883 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 2.7459. Min Range: -2.7459

Max Act: 2.3675. Min Act: -0.0000

Data Index: 271364 (C4 (Web Text))

Max Activating Token Index: 373