Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2756 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2600. Min Act: -0.0001

Data Index: 254355 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2514. Min Act: -0.0001

Data Index: 145816 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2301. Min Act: -0.0001

Data Index: 305179 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2351. Min Act: -0.0001

Data Index: 8546 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2277. Min Act: -0.0001

Data Index: 107250 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2247. Min Act: -0.0001

Data Index: 284242 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2190. Min Act: -0.0001

Data Index: 896087 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2178. Min Act: -0.0001

Data Index: 994440 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2112. Min Act: -0.0001

Data Index: 719041 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2016. Min Act: -0.0001

Data Index: 1093055 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2056. Min Act: -0.0001

Data Index: 283430 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1273795 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2062. Min Act: -0.0001

Data Index: 430951 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1151688 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1968. Min Act: -0.0001

Data Index: 670281 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1876. Min Act: -0.0001

Data Index: 486016 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.2038. Min Act: -0.0001

Data Index: 913663 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1907. Min Act: -0.0001

Data Index: 547247 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1925. Min Act: -0.0001

Data Index: 787840 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.2600. Min Range: -0.2600

Max Act: 0.1949. Min Act: -0.0001

Data Index: 281395 (C4 (Web Text))

Max Activating Token Index: 52