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

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

Neuron 2752 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9874. Min Act: -0.0000

Data Index: 463951 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.9149. Min Act: -0.0000

Data Index: 879381 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.8617. Min Act: -0.0000

Data Index: 835568 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1207740 (C4 (Web Text))

Max Activating Token Index: 202

Text #4

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.6628. Min Act: -0.0000

Data Index: 119147 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1281349 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1105552 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5898. Min Act: -0.0000

Data Index: 434854 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5995. Min Act: -0.0000

Data Index: 362819 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1258515 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5276. Min Act: -0.0000

Data Index: 929973 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1182968 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5178. Min Act: -0.0000

Data Index: 177701 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5182. Min Act: -0.0000

Data Index: 1283210 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.4849. Min Act: -0.0000

Data Index: 983776 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1156675 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1074068 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5018. Min Act: -0.0000

Data Index: 45676 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.5022. Min Act: -0.0000

Data Index: 514079 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.9874. Min Range: -0.9874

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1308385 (C4 (Web Text))

Max Activating Token Index: 475