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

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

Neuron 1441 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4408. Min Act: -0.0002

Data Index: 68482 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4458. Min Act: -0.0002

Data Index: 650349 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4652. Min Act: -0.0003

Data Index: 951108 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4176. Min Act: -0.0003

Data Index: 435451 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4181. Min Act: -0.0002

Data Index: 1187081 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4292. Min Act: -0.0002

Data Index: 82630 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3998. Min Act: -0.0003

Data Index: 414047 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4091. Min Act: -0.0003

Data Index: 1075787 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.4087. Min Act: -0.0003

Data Index: 401138 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3797. Min Act: -0.0003

Data Index: 1316025 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3913. Min Act: -0.0002

Data Index: 623304 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3598. Min Act: -0.0002

Data Index: 607860 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3724. Min Act: -0.0003

Data Index: 1162385 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3843. Min Act: -0.0002

Data Index: 1302765 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3560. Min Act: -0.0003

Data Index: 137017 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3443. Min Act: -0.0003

Data Index: 272618 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3703. Min Act: -0.0003

Data Index: 480632 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3526. Min Act: -0.0003

Data Index: 1104720 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3487. Min Act: -0.0003

Data Index: 127717 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.4652. Min Range: -0.4652

Max Act: 0.3057. Min Act: -0.0003

Data Index: 252773 (C4 (Web Text))

Max Activating Token Index: 704