Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1339 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.1602. Min Act: -0.0000

Data Index: 710544 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0917. Min Act: -0.0000

Data Index: 154675 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0893. Min Act: -0.0000

Data Index: 632243 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0802. Min Act: -0.0000

Data Index: 26924 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0759. Min Act: -0.0000

Data Index: 713887 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0787. Min Act: -0.0000

Data Index: 1173269 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0837. Min Act: -0.0000

Data Index: 114722 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0748. Min Act: -0.0000

Data Index: 464292 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1336926 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0690. Min Act: -0.0000

Data Index: 197499 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0685. Min Act: -0.0000

Data Index: 102581 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0684. Min Act: -0.0000

Data Index: 259216 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1067733 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0624. Min Act: -0.0000

Data Index: 301313 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1216407 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0653. Min Act: -0.0000

Data Index: 540300 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0656. Min Act: -0.0000

Data Index: 185131 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1070467 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0569. Min Act: -0.0000

Data Index: 569128 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 0.1602. Min Range: -0.1602

Max Act: 0.0604. Min Act: -0.0000

Data Index: 577224 (C4 (Web Text))

Max Activating Token Index: 927