Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5175 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1175. Min Range: -5.1175

Max Act: 5.1175. Min Act: -0.0000

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.6789. Min Act: -0.0000

Data Index: 56423 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.6490. Min Act: -0.0000

Data Index: 925368 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.6314. Min Act: -0.0000

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.2115. Min Act: -0.0000

Data Index: 452876 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.1852. Min Act: -0.0000

Data Index: 418741 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.1254. Min Act: -0.0000

Data Index: 805922 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 5.1175. Min Range: -5.1175

Max Act: 4.0020. Min Act: -0.0000

Data Index: 103974 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.6871. Min Act: -0.0000

Data Index: 6453 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.6766. Min Act: -0.0000

Data Index: 346656 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.5923. Min Act: -0.0000

Data Index: 899142 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.5705. Min Act: -0.0000

Data Index: 117955 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.6731. Min Act: -0.0000

Data Index: 306873 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.3116. Min Act: -0.0000

Data Index: 438421 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.4547. Min Act: -0.0000

Data Index: 646777 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.2420. Min Act: -0.0000

Data Index: 398539 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.2091. Min Act: -0.0000

Data Index: 33918 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.0356. Min Act: -0.0000

Data Index: 607877 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.2049. Min Act: -0.0000

Data Index: 355411 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 5.1175. Min Range: -5.1175

Max Act: 3.1941. Min Act: -0.0000

Data Index: 610997 (C4 (Web Text))

Max Activating Token Index: 414