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

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

Neuron 4067 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3333. Min Range: -2.3333

Max Act: 2.3333. Min Act: -0.0000

Data Index: 767447 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1278727 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1083139 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1352416 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.6635. Min Act: -0.0000

Data Index: 592097 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.7357. Min Act: -0.0000

Data Index: 619673 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.5919. Min Act: -0.0000

Data Index: 846600 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4934. Min Act: -0.0000

Data Index: 421749 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4665. Min Act: -0.0000

Data Index: 238826 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1338734 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3597. Min Act: -0.0000

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2793. Min Act: -0.0000

Data Index: 296971 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3072. Min Act: -0.0000

Data Index: 807595 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1271347 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2983. Min Act: -0.0000

Data Index: 768858 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2951. Min Act: -0.0000

Data Index: 24937 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.5067. Min Act: -0.0000

Data Index: 785141 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.3657. Min Act: -0.0000

Data Index: 142563 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2144. Min Act: -0.0000

Data Index: 978807 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 2.3333. Min Range: -2.3333

Max Act: 1.2731. Min Act: -0.0000

Data Index: 101470 (C4 (Web Text))

Max Activating Token Index: 852