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

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

Neuron 1798 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5166. Min Act: -0.0001

Data Index: 258309 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5663. Min Act: -0.0001

Data Index: 995535 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5403. Min Act: -0.0001

Data Index: 461272 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4302. Min Act: -0.0001

Data Index: 582842 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5052. Min Act: -0.0001

Data Index: 308501 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5189. Min Act: -0.0001

Data Index: 413418 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5051. Min Act: -0.0001

Data Index: 45679 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4912. Min Act: -0.0001

Data Index: 299209 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4855. Min Act: -0.0001

Data Index: 175955 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5355. Min Act: -0.0001

Data Index: 413618 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4792. Min Act: -0.0001

Data Index: 1268018 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4465. Min Act: -0.0001

Data Index: 836720 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4369. Min Act: -0.0001

Data Index: 69911 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4593. Min Act: -0.0001

Data Index: 916618 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.5118. Min Act: -0.0001

Data Index: 284733 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4426. Min Act: -0.0001

Data Index: 420687 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4534. Min Act: -0.0001

Data Index: 812181 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4341. Min Act: -0.0001

Data Index: 599131 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4470. Min Act: -0.0001

Data Index: 911359 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 0.5663. Min Range: -0.5663

Max Act: 0.4468. Min Act: -0.0001

Data Index: 498556 (C4 (Web Text))

Max Activating Token Index: 450