Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1734 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0003

Data Index: 1278890 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0797. Min Act: -0.0002

Data Index: 503282 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0771. Min Act: -0.0003

Data Index: 810186 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0696. Min Act: -0.0003

Data Index: 1259694 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0643. Min Act: -0.0004

Data Index: 685846 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1346991 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0677. Min Act: -0.0003

Data Index: 598290 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0632. Min Act: -0.0003

Data Index: 726170 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1318275 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1170134 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0638. Min Act: -0.0003

Data Index: 580349 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0621. Min Act: -0.0003

Data Index: 388268 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1091979 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0646. Min Act: -0.0003

Data Index: 28236 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1047624 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0645. Min Act: -0.0003

Data Index: 357007 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0625. Min Act: -0.0003

Data Index: 788702 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1158351 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0621. Min Act: -0.0002

Data Index: 13412 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1248608 (C4 (Web Text))

Max Activating Token Index: 70