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

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

Neuron 536 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: 1.3097. Min Range: -1.3097

Max Act: 1.3097. Min Act: -0.0000

Data Index: 150236 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.2074. Min Act: -0.0000

Data Index: 367605 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.1777. Min Act: -0.0000

Data Index: 384762 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.1297. Min Act: -0.0000

Data Index: 87415 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1310899 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0858. Min Act: -0.0000

Data Index: 982183 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1056898 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1248339 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0845. Min Act: -0.0001

Data Index: 85394 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9196. Min Act: -0.0000

Data Index: 225385 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0406. Min Act: -0.0000

Data Index: 1267607 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1339048 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 1.3097. Min Range: -1.3097

Max Act: 1.0322. Min Act: -0.0001

Data Index: 34195 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9539. Min Act: -0.0000

Data Index: 160387 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1285199 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.8733. Min Act: -0.0000

Data Index: 898687 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9258. Min Act: -0.0000

Data Index: 529030 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9577. Min Act: -0.0001

Data Index: 861387 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9146. Min Act: -0.0000

Data Index: 426087 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 1.3097. Min Range: -1.3097

Max Act: 0.9441. Min Act: -0.0000

Data Index: 719696 (C4 (Web Text))

Max Activating Token Index: 1006