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

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

Neuron 3988 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5412. Min Range: -4.5412

Max Act: 4.5412. Min Act: -0.0000

Data Index: 840244 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.8518. Min Act: -0.0000

Data Index: 761340 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 4.5412. Min Range: -4.5412

Max Act: 4.2091. Min Act: -0.0000

Data Index: 1109393 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.6394. Min Act: -0.0000

Data Index: 1425938 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.7287. Min Act: 0.0000

Data Index: 1498283 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.4107. Min Act: -0.0000

Data Index: 1465621 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.5487. Min Act: -0.0000

Data Index: 1134149 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.1669. Min Act: -0.0000

Data Index: 1292876 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.8803. Min Act: -0.0000

Data Index: 516858 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.1769. Min Act: -0.0000

Data Index: 559007 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.0456. Min Act: -0.0000

Data Index: 1434266 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 4.5412. Min Range: -4.5412

Max Act: 3.1737. Min Act: -0.0000

Data Index: 388375 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.8678. Min Act: -0.0000

Data Index: 1451305 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.9971. Min Act: -0.0000

Data Index: 1575736 (Python Code)

Max Activating Token Index: 397

Text #14

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.9486. Min Act: -0.0000

Data Index: 1161128 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.9824. Min Act: -0.0000

Data Index: 459581 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.8282. Min Act: -0.0000

Data Index: 434574 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.8162. Min Act: -0.0000

Data Index: 1621589 (Python Code)

Max Activating Token Index: 773

Text #18

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.7895. Min Act: -0.0000

Data Index: 739140 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 4.5412. Min Range: -4.5412

Max Act: 2.6521. Min Act: -0.0000

Data Index: 757068 (C4 (Web Text))

Max Activating Token Index: 904