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

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

Neuron 2002 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: 2.2002. Min Range: -2.2002

Max Act: 2.2002. Min Act: -0.0000

Data Index: 176362 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.9653. Min Act: -0.0000

Data Index: 399332 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.9181. Min Act: -0.0000

Data Index: 118897 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.8433. Min Act: -0.0000

Data Index: 899853 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.9067. Min Act: -0.0000

Data Index: 1645043 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7450. Min Act: -0.0000

Data Index: 362046 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.8023. Min Act: -0.0000

Data Index: 575176 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.8097. Min Act: -0.0000

Data Index: 183386 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.9035. Min Act: -0.0000

Data Index: 425023 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7781. Min Act: -0.0000

Data Index: 252419 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.8081. Min Act: -0.0000

Data Index: 1319172 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.5619. Min Act: -0.0000

Data Index: 320580 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7111. Min Act: -0.0000

Data Index: 847616 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7533. Min Act: -0.0000

Data Index: 1625930 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7255. Min Act: -0.0000

Data Index: 296149 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1147997 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7323. Min Act: -0.0000

Data Index: 80121 (C4 (Web Text))

Max Activating Token Index: 72

Text #17

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7813. Min Act: -0.0000

Data Index: 881056 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.7282. Min Act: -0.0000

Data Index: 556213 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 2.2002. Min Range: -2.2002

Max Act: 1.6751. Min Act: -0.0000

Data Index: 952446 (C4 (Web Text))

Max Activating Token Index: 608