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

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

Neuron 4502 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.2150. Min Act: -0.0000

Data Index: 520 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.3320. Min Act: -0.0000

Data Index: 1130774 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.2274. Min Act: -0.0000

Data Index: 564260 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.2214. Min Act: -0.0000

Data Index: 926885 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.2593. Min Act: -0.0000

Data Index: 253642 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.1778. Min Act: -0.0000

Data Index: 904969 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.1285. Min Act: -0.0000

Data Index: 162648 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.1080. Min Act: -0.0000

Data Index: 283801 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0986. Min Act: -0.0000

Data Index: 524881 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1237143 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.1618. Min Act: -0.0000

Data Index: 209753 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.3320. Min Range: -1.3320

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1038691 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1250511 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0652. Min Act: -0.0000

Data Index: 555728 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0263. Min Act: -0.0000

Data Index: 37846 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1153657 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 1.3320. Min Range: -1.3320

Max Act: 1.0062. Min Act: -0.0000

Data Index: 931945 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 1.3320. Min Range: -1.3320

Max Act: 0.9431. Min Act: -0.0000

Data Index: 251379 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.3320. Min Range: -1.3320

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1341142 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 1.3320. Min Range: -1.3320

Max Act: 0.9865. Min Act: -0.0000

Data Index: 756442 (C4 (Web Text))

Max Activating Token Index: 935