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

Dataset: The Pile

Neuron 1189 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.3206. Min Range: -12.3206

Max Act: 12.3206. Min Act: -0.0000

Data Index: 1508223 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.9946. Min Act: -0.0000

Data Index: 477934 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 12.3206. Min Range: -12.3206

Max Act: 12.0607. Min Act: -0.0000

Data Index: 1987049 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 12.3206. Min Range: -12.3206

Max Act: 12.0420. Min Act: -0.0000

Data Index: 251831 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 12.3206. Min Range: -12.3206

Max Act: 12.0428. Min Act: -0.0000

Data Index: 1121603 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 12.3206. Min Range: -12.3206

Max Act: 12.0171. Min Act: -0.0000

Data Index: 1086021 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.8029. Min Act: -0.0000

Data Index: 924995 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.9923. Min Act: -0.0000

Data Index: 1331690 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.9546. Min Act: -0.0000

Data Index: 308018 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.4212. Min Act: -0.0000

Data Index: 1654002 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.6674. Min Act: -0.0000

Data Index: 1883945 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.9573. Min Act: -0.0000

Data Index: 754781 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.8828. Min Act: -0.0000

Data Index: 44084 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.8602. Min Act: -0.0000

Data Index: 930589 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.4652. Min Act: -0.0000

Data Index: 1239556 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.7008. Min Act: -0.0000

Data Index: 485772 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.7800. Min Act: -0.0000

Data Index: 1082991 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.7612. Min Act: -0.0000

Data Index: 1763944 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.5720. Min Act: -0.0000

Data Index: 422849 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 12.3206. Min Range: -12.3206

Max Act: 11.3011. Min Act: -0.0000

Data Index: 570221 (The Pile)

Max Activating Token Index: 751