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

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

Neuron 140 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1177500 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1648. Min Act: -0.0001

Data Index: 796282 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1061742 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1400. Min Act: -0.0001

Data Index: 134932 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1352. Min Act: -0.0001

Data Index: 1046803 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1272. Min Act: -0.0001

Data Index: 902033 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1509. Min Act: -0.0001

Data Index: 647780 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1209029 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1411. Min Act: -0.0001

Data Index: 125605 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1316. Min Act: -0.0001

Data Index: 97132 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1159. Min Act: -0.0001

Data Index: 935667 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1237. Min Act: -0.0001

Data Index: 649335 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1250. Min Act: -0.0001

Data Index: 367167 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1163. Min Act: -0.0001

Data Index: 281560 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1296. Min Act: -0.0001

Data Index: 535642 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1248. Min Act: -0.0001

Data Index: 508729 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1171. Min Act: -0.0001

Data Index: 259293 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1008115 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1214. Min Act: -0.0001

Data Index: 491621 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.1931. Min Range: -0.1931

Max Act: 0.1266. Min Act: -0.0001

Data Index: 665170 (C4 (Web Text))

Max Activating Token Index: 906