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

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

Neuron 3383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.8389. Min Act: -0.0000

Data Index: 631280 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.7136. Min Act: -0.0000

Data Index: 1125097 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.5027. Min Act: -0.0000

Data Index: 230211 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.4607. Min Act: -0.0000

Data Index: 1239898 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.5094. Min Act: -0.0000

Data Index: 519254 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.3926. Min Act: -0.0000

Data Index: 788782 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.3675. Min Act: -0.0000

Data Index: 1210496 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.3238. Min Act: -0.0000

Data Index: 1325095 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.4028. Min Act: -0.0000

Data Index: 884716 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.1628. Min Act: -0.0000

Data Index: 175679 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.3775. Min Act: -0.0000

Data Index: 260292 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.2229. Min Act: -0.0000

Data Index: 930457 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1079980 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.1963. Min Act: -0.0000

Data Index: 910414 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.1743. Min Act: -0.0000

Data Index: 582333 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.0239. Min Act: -0.0000

Data Index: 1005110 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 2.8389. Min Range: -2.8389

Max Act: 1.9891. Min Act: -0.0000

Data Index: 900784 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.0299. Min Act: -0.0000

Data Index: 323933 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.1662. Min Act: -0.0000

Data Index: 541668 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 2.8389. Min Range: -2.8389

Max Act: 2.0098. Min Act: -0.0000

Data Index: 352824 (C4 (Web Text))

Max Activating Token Index: 69