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

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

Neuron 2910 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0696. Min Range: -2.0696

Max Act: 2.0696. Min Act: -0.0000

Data Index: 899469 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.7515. Min Act: -0.0000

Data Index: 1253995 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8417. Min Act: -0.0000

Data Index: 56595 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.6675. Min Act: -0.0000

Data Index: 227837 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.8112. Min Act: -0.0000

Data Index: 4656 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.5706. Min Act: -0.0000

Data Index: 862699 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.5514. Min Act: -0.0000

Data Index: 54240 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.5306. Min Act: -0.0000

Data Index: 304215 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1183388 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.4512. Min Act: -0.0000

Data Index: 560775 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.2207. Min Act: -0.0000

Data Index: 305036 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.3167. Min Act: -0.0000

Data Index: 465491 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.2794. Min Act: -0.0000

Data Index: 598679 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.3060. Min Act: -0.0000

Data Index: 701181 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.4161. Min Act: -0.0000

Data Index: 842222 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.3309. Min Act: -0.0000

Data Index: 643841 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.3634. Min Act: -0.0000

Data Index: 219551 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.2803. Min Act: -0.0000

Data Index: 452702 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.2401. Min Act: -0.0000

Data Index: 623873 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.0696. Min Range: -2.0696

Max Act: 1.3661. Min Act: -0.0000

Data Index: 265085 (C4 (Web Text))

Max Activating Token Index: 665