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

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

Neuron 2218 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1275332 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.9210. Min Act: -0.0000

Data Index: 830814 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.0072. Min Range: -1.0072

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1228287 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.9114. Min Act: -0.0000

Data Index: 322103 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8804. Min Act: -0.0000

Data Index: 900054 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7285. Min Act: -0.0000

Data Index: 898407 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7378. Min Act: -0.0000

Data Index: 910285 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7144. Min Act: -0.0000

Data Index: 147279 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7042. Min Act: -0.0000

Data Index: 735806 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6966. Min Act: -0.0000

Data Index: 179975 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7128. Min Act: -0.0000

Data Index: 987987 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6586. Min Act: -0.0000

Data Index: 129495 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6553. Min Act: -0.0000

Data Index: 611469 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6737. Min Act: -0.0000

Data Index: 458961 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6323. Min Act: -0.0000

Data Index: 480117 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1295157 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1129036 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6030. Min Act: -0.0000

Data Index: 184656 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.5843. Min Act: -0.0000

Data Index: 655057 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.6016. Min Act: -0.0000

Data Index: 405668 (C4 (Web Text))

Max Activating Token Index: 452