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

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

Neuron 4518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9139. Min Range: -4.9139

Max Act: 4.6756. Min Act: -0.0001

Data Index: 1123738 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 4.9139. Min Range: -4.9139

Max Act: 4.4593. Min Act: -0.0000

Data Index: 409339 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 4.9139. Min Range: -4.9139

Max Act: 4.9139. Min Act: -0.0000

Data Index: 1139538 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 4.9139. Min Range: -4.9139

Max Act: 4.3109. Min Act: -0.0000

Data Index: 318958 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 4.9139. Min Range: -4.9139

Max Act: 4.0848. Min Act: -0.0000

Data Index: 1050857 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.8336. Min Act: -0.0000

Data Index: 1280979 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.7689. Min Act: -0.0000

Data Index: 485322 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.8106. Min Act: -0.0000

Data Index: 1242840 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.6155. Min Act: -0.0000

Data Index: 352109 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.5687. Min Act: -0.0000

Data Index: 559983 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.7210. Min Act: -0.0000

Data Index: 641665 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.5294. Min Act: -0.0000

Data Index: 953317 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.7056. Min Act: -0.0000

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.6771. Min Act: -0.0000

Data Index: 186238 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.4913. Min Act: -0.0000

Data Index: 1411459 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.3155. Min Act: -0.0000

Data Index: 27538 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.4566. Min Act: -0.0000

Data Index: 564565 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.4289. Min Act: -0.0000

Data Index: 635337 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.5639. Min Act: -0.0000

Data Index: 968567 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 4.9139. Min Range: -4.9139

Max Act: 3.5411. Min Act: -0.0000

Data Index: 753708 (C4 (Web Text))

Max Activating Token Index: 476