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

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

Neuron 618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.8758. Min Act: -0.0001

Data Index: 1197254 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6831. Min Act: -0.0001

Data Index: 231427 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6683. Min Act: -0.0000

Data Index: 789461 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6059. Min Act: -0.0001

Data Index: 720754 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5775. Min Act: -0.0001

Data Index: 88190 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5215. Min Act: -0.0000

Data Index: 824230 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5433. Min Act: -0.0001

Data Index: 437372 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1049053 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5368. Min Act: -0.0001

Data Index: 798812 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4555. Min Act: -0.0000

Data Index: 876113 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4963. Min Act: -0.0001

Data Index: 597156 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5153. Min Act: -0.0001

Data Index: 970318 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4897. Min Act: -0.0001

Data Index: 278176 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4259. Min Act: -0.0001

Data Index: 1316676 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4513. Min Act: -0.0001

Data Index: 270799 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4287. Min Act: -0.0001

Data Index: 337027 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1006712 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.3702. Min Act: -0.0001

Data Index: 634992 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.3779. Min Act: -0.0001

Data Index: 266691 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.3916. Min Act: -0.0001

Data Index: 890032 (C4 (Web Text))

Max Activating Token Index: 958