Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 812 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5594. Min Act: -0.0001

Data Index: 1436488 (Python Code)

Max Activating Token Index: 643

Text #1

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5000. Min Act: -0.0001

Data Index: 115757 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1571999 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4794. Min Act: -0.0001

Data Index: 844385 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4757. Min Act: -0.0001

Data Index: 1605668 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4908. Min Act: -0.0001

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4864. Min Act: -0.0001

Data Index: 1397770 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4510. Min Act: -0.0001

Data Index: 367372 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4650. Min Act: -0.0001

Data Index: 1642699 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1370875 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1406812 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1647747 (Python Code)

Max Activating Token Index: 493

Text #12

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4736. Min Act: -0.0000

Data Index: 452188 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4440. Min Act: -0.0001

Data Index: 750663 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4541. Min Act: -0.0001

Data Index: 769530 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4386. Min Act: -0.0001

Data Index: 1160800 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1133987 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1602319 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4607. Min Act: -0.0000

Data Index: 746833 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4140. Min Act: -0.0001

Data Index: 751037 (C4 (Web Text))

Max Activating Token Index: 72