Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4414 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.8288. Min Act: -0.0001

Data Index: 328604 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.8330. Min Act: -0.0000

Data Index: 604395 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.8768. Min Act: -0.0000

Data Index: 505014 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1169816 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.7270. Min Act: -0.0000

Data Index: 618009 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6817. Min Act: -0.0001

Data Index: 86410 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1165591 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6263. Min Act: -0.0000

Data Index: 56769 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6119. Min Act: -0.0000

Data Index: 450859 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1328915 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5609. Min Act: -0.0001

Data Index: 804457 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5903. Min Act: -0.0001

Data Index: 404112 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6043. Min Act: -0.0001

Data Index: 519989 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1203394 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1282597 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5630. Min Act: -0.0000

Data Index: 962181 (C4 (Web Text))

Max Activating Token Index: 321

Text #16

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5416. Min Act: -0.0000

Data Index: 242476 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5210. Min Act: -0.0001

Data Index: 305729 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1121878 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.8768. Min Range: -0.8768

Max Act: 0.4761. Min Act: -0.0000

Data Index: 1291419 (C4 (Web Text))

Max Activating Token Index: 407