Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2630 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.4059. Min Act: -0.0001

Data Index: 1042186 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.3444. Min Act: -0.0001

Data Index: 224165 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1813. Min Act: -0.0001

Data Index: 436337 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.2135. Min Act: -0.0001

Data Index: 661121 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1558. Min Act: -0.0001

Data Index: 1085207 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1840. Min Act: -0.0001

Data Index: 260306 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1091. Min Act: -0.0001

Data Index: 627286 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.1693. Min Act: -0.0001

Data Index: 1135909 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0430. Min Act: -0.0001

Data Index: 326521 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0542. Min Act: -0.0001

Data Index: 130370 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0674. Min Act: -0.0001

Data Index: 1196759 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0546. Min Act: -0.0001

Data Index: 576792 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0035. Min Act: -0.0001

Data Index: 1253633 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0055. Min Act: -0.0001

Data Index: 404287 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0408. Min Act: -0.0001

Data Index: 1096941 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0070. Min Act: -0.0001

Data Index: 1278016 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0222. Min Act: -0.0001

Data Index: 1146190 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.4059. Min Range: -1.4059

Max Act: 1.0019. Min Act: -0.0001

Data Index: 1272712 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9336. Min Act: -0.0001

Data Index: 748790 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 1.4059. Min Range: -1.4059

Max Act: 0.9650. Min Act: -0.0001

Data Index: 470900 (C4 (Web Text))

Max Activating Token Index: 319