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

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

Neuron 4066 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1256. Min Range: -3.1256

Max Act: 3.1256. Min Act: -0.0001

Data Index: 147440 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.9457. Min Act: -0.0002

Data Index: 86116 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.7668. Min Act: -0.0001

Data Index: 70115 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.6537. Min Act: -0.0001

Data Index: 238221 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.4402. Min Act: -0.0001

Data Index: 1287581 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.5022. Min Act: -0.0001

Data Index: 132964 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.6786. Min Act: -0.0002

Data Index: 94075 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.4292. Min Act: -0.0001

Data Index: 969165 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9991. Min Act: -0.0001

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9590. Min Act: -0.0001

Data Index: 284950 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.3854. Min Act: -0.0002

Data Index: 336970 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9871. Min Act: -0.0001

Data Index: 624977 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.2110. Min Act: -0.0001

Data Index: 28447 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.2452. Min Act: -0.0001

Data Index: 67211 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.0085. Min Act: -0.0001

Data Index: 690288 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 3.1256. Min Range: -3.1256

Max Act: 2.0517. Min Act: -0.0001

Data Index: 1240310 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.8668. Min Act: -0.0001

Data Index: 761867 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9577. Min Act: -0.0001

Data Index: 409707 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9155. Min Act: -0.0001

Data Index: 847603 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 3.1256. Min Range: -3.1256

Max Act: 1.9628. Min Act: -0.0002

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 916