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

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

Neuron 2638 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.2543. Min Act: -0.0000

Data Index: 598134 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3280. Min Act: -0.0000

Data Index: 882459 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.4317. Min Act: -0.0000

Data Index: 810751 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.4256. Min Act: -0.0000

Data Index: 665162 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.1129. Min Act: -0.0000

Data Index: 143241 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0732. Min Act: -0.0000

Data Index: 756698 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.3380. Min Act: -0.0000

Data Index: 377311 (C4 (Web Text))

Max Activating Token Index: 320

Text #7

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.9568. Min Act: -0.0000

Data Index: 1196114 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0863. Min Act: -0.0000

Data Index: 1142582 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0815. Min Act: -0.0000

Data Index: 502379 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0653. Min Act: -0.0000

Data Index: 161714 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0520. Min Act: -0.0000

Data Index: 1143224 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.8622. Min Act: -0.0000

Data Index: 213826 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.9961. Min Act: -0.0000

Data Index: 153750 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.2563. Min Act: -0.0000

Data Index: 912500 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.9577. Min Act: -0.0000

Data Index: 1540911 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 3.4317. Min Range: -3.4317

Max Act: 3.0988. Min Act: -0.0000

Data Index: 937680 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.9380. Min Act: -0.0000

Data Index: 74880 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.7954. Min Act: -0.0000

Data Index: 1125322 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 3.4317. Min Range: -3.4317

Max Act: 2.7718. Min Act: -0.0000

Data Index: 1157264 (C4 (Web Text))

Max Activating Token Index: 62