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

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

Neuron 1038 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: 3.1114. Min Range: -3.1114

Max Act: 3.1114. Min Act: -0.0000

Data Index: 581663 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 3.1114. Min Range: -3.1114

Max Act: 2.4033. Min Act: -0.0000

Data Index: 260811 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 3.1114. Min Range: -3.1114

Max Act: 2.0688. Min Act: -0.0000

Data Index: 955535 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 3.1114. Min Range: -3.1114

Max Act: 2.1713. Min Act: -0.0000

Data Index: 655548 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.1114. Min Range: -3.1114

Max Act: 2.0494. Min Act: -0.0000

Data Index: 31637 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.9339. Min Act: -0.0000

Data Index: 302262 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.7141. Min Act: -0.0000

Data Index: 1166223 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.8160. Min Act: -0.0000

Data Index: 900619 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1014557 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.7401. Min Act: -0.0000

Data Index: 1459169 (Python Code)

Max Activating Token Index: 754

Text #10

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1595189 (Python Code)

Max Activating Token Index: 733

Text #11

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.6507. Min Act: -0.0000

Data Index: 491248 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1599711 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1485275 (Python Code)

Max Activating Token Index: 733

Text #14

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.3686. Min Act: -0.0000

Data Index: 1215693 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.3627. Min Act: -0.0000

Data Index: 132387 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.4402. Min Act: -0.0000

Data Index: 401702 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.5330. Min Act: -0.0000

Data Index: 496607 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.4224. Min Act: -0.0000

Data Index: 855306 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 3.1114. Min Range: -3.1114

Max Act: 1.4343. Min Act: -0.0000

Data Index: 71266 (C4 (Web Text))

Max Activating Token Index: 579