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

Dataset: The Pile

Neuron 4695 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1998653 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1194839 (The Pile)

Max Activating Token Index: 693

Text #2

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4020. Min Act: -0.0000

Data Index: 651020 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4588. Min Act: -0.0000

Data Index: 769031 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4966. Min Act: -0.0000

Data Index: 425994 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1831194 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3227. Min Act: -0.0000

Data Index: 1229380 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3726. Min Act: -0.0000

Data Index: 485884 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2695. Min Act: -0.0000

Data Index: 1038060 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1205866 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4244. Min Act: -0.0000

Data Index: 595887 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1195140 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3372. Min Act: -0.0000

Data Index: 679852 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1047413 (The Pile)

Max Activating Token Index: 560

Text #14

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1401339 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2454. Min Act: -0.0000

Data Index: 725130 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.3253. Min Act: -0.0000

Data Index: 257553 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.2363. Min Act: -0.0000

Data Index: 1184825 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1085984 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.6233. Min Range: -1.6233

Max Act: 1.1806. Min Act: -0.0000

Data Index: 1282506 (The Pile)

Max Activating Token Index: 377