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

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

Neuron 340 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2666. Min Range: -1.2666

Max Act: 1.2666. Min Act: -0.0001

Data Index: 111582 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 1.2666. Min Range: -1.2666

Max Act: 1.0893. Min Act: -0.0001

Data Index: 1313219 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.9041. Min Act: -0.0001

Data Index: 977619 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.7877. Min Act: -0.0001

Data Index: 587791 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.7724. Min Act: -0.0001

Data Index: 51370 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6147. Min Act: -0.0001

Data Index: 172914 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6425. Min Act: -0.0001

Data Index: 277205 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5889. Min Act: -0.0001

Data Index: 1243265 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6232. Min Act: -0.0001

Data Index: 1152585 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6275. Min Act: -0.0001

Data Index: 923124 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6256. Min Act: -0.0001

Data Index: 1018167 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5972. Min Act: -0.0001

Data Index: 835567 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1074224 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5338. Min Act: -0.0001

Data Index: 1107089 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5625. Min Act: -0.0001

Data Index: 29970 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5287. Min Act: -0.0001

Data Index: 347512 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5409. Min Act: -0.0001

Data Index: 1300368 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5091. Min Act: -0.0001

Data Index: 128168 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5167. Min Act: -0.0001

Data Index: 1313163 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.2666. Min Range: -1.2666

Max Act: 0.5176. Min Act: -0.0001

Data Index: 1147110 (C4 (Web Text))

Max Activating Token Index: 331