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

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

Neuron 4382 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: 2.3872. Min Range: -2.3872

Max Act: 2.3357. Min Act: -0.0000

Data Index: 1126345 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 2.3872. Min Range: -2.3872

Max Act: 2.3872. Min Act: -0.0000

Data Index: 988133 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.9511. Min Act: -0.0000

Data Index: 384762 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.9414. Min Act: -0.0000

Data Index: 1184745 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.5174. Min Act: -0.0000

Data Index: 942572 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.6035. Min Act: -0.0000

Data Index: 1233198 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.5923. Min Act: -0.0000

Data Index: 604621 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1083945 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1129561 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.5116. Min Act: -0.0000

Data Index: 1122189 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.4950. Min Act: -0.0000

Data Index: 40307 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.7259. Min Act: -0.0000

Data Index: 1319322 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.4782. Min Act: -0.0000

Data Index: 836783 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.4148. Min Act: -0.0000

Data Index: 743318 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.3897. Min Act: -0.0000

Data Index: 264025 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.3374. Min Act: -0.0000

Data Index: 230556 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.4120. Min Act: -0.0000

Data Index: 1080444 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.3574. Min Act: -0.0000

Data Index: 529209 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.3810. Min Act: -0.0000

Data Index: 443500 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 2.3872. Min Range: -2.3872

Max Act: 1.2613. Min Act: -0.0000

Data Index: 712340 (C4 (Web Text))

Max Activating Token Index: 815