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

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

Neuron 217 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: 1.7018. Min Range: -1.7018

Max Act: 1.7018. Min Act: -0.0001

Data Index: 9765 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.6720. Min Act: -0.0001

Data Index: 361171 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.6306. Min Act: -0.0001

Data Index: 1213965 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.3883. Min Act: -0.0001

Data Index: 1260725 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2065. Min Act: -0.0001

Data Index: 776377 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1960. Min Act: -0.0001

Data Index: 61334 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2665. Min Act: -0.0001

Data Index: 820143 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1572. Min Act: -0.0001

Data Index: 173653 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2215. Min Act: -0.0001

Data Index: 238288 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.2471. Min Act: -0.0001

Data Index: 1312905 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1890. Min Act: -0.0001

Data Index: 351411 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1788. Min Act: -0.0001

Data Index: 1274515 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1423. Min Act: -0.0001

Data Index: 95795 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.1249. Min Act: -0.0001

Data Index: 322185 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0989. Min Act: -0.0001

Data Index: 958461 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0849. Min Act: -0.0001

Data Index: 830573 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0801. Min Act: -0.0001

Data Index: 1053219 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0236. Min Act: -0.0001

Data Index: 1047740 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0482. Min Act: -0.0001

Data Index: 1246089 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 1.7018. Min Range: -1.7018

Max Act: 1.0618. Min Act: -0.0001

Data Index: 890058 (C4 (Web Text))

Max Activating Token Index: 776