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

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

Neuron 517 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8854. Min Act: -0.0000

Data Index: 306070 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.8814. Min Act: -0.0000

Data Index: 1283901 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.7391. Min Act: -0.0000

Data Index: 371299 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.7016. Min Act: -0.0001

Data Index: 434599 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.7325. Min Act: -0.0000

Data Index: 713065 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1181610 (C4 (Web Text))

Max Activating Token Index: 617

Text #6

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6169. Min Act: -0.0000

Data Index: 100696 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.6484. Min Act: -0.0000

Data Index: 496319 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5455. Min Act: -0.0000

Data Index: 293962 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5679. Min Act: -0.0001

Data Index: 408960 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5248. Min Act: -0.0001

Data Index: 699512 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.5529. Min Act: -0.0000

Data Index: 794138 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4906. Min Act: -0.0001

Data Index: 920341 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4372. Min Act: -0.0000

Data Index: 294385 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4433. Min Act: -0.0000

Data Index: 728332 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4194. Min Act: -0.0000

Data Index: 909254 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4196. Min Act: -0.0000

Data Index: 193351 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4106. Min Act: -0.0000

Data Index: 693080 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.4015. Min Act: -0.0001

Data Index: 296339 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 1.8854. Min Range: -1.8854

Max Act: 1.3532. Min Act: -0.0000

Data Index: 327262 (C4 (Web Text))

Max Activating Token Index: 777