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

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

Neuron 166 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.3944. Min Act: -0.0000

Data Index: 607701 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.3429. Min Act: -0.0000

Data Index: 654622 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.3762. Min Act: -0.0000

Data Index: 120173 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.3351. Min Act: -0.0000

Data Index: 626066 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2893. Min Act: -0.0000

Data Index: 690713 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2966. Min Act: -0.0000

Data Index: 699656 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2894. Min Act: -0.0000

Data Index: 595809 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2794. Min Act: -0.0000

Data Index: 526996 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2731. Min Act: -0.0000

Data Index: 13637 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2684. Min Act: -0.0000

Data Index: 252573 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2557. Min Act: -0.0000

Data Index: 557796 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2531. Min Act: -0.0000

Data Index: 499469 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1212520 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2529. Min Act: -0.0000

Data Index: 964552 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2584. Min Act: -0.0000

Data Index: 799477 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2471. Min Act: -0.0000

Data Index: 979133 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2465. Min Act: -0.0000

Data Index: 826048 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2374. Min Act: -0.0000

Data Index: 340624 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1281094 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.3944. Min Range: -0.3944

Max Act: 0.2099. Min Act: -0.0000

Data Index: 382616 (C4 (Web Text))

Max Activating Token Index: 651