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

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

Neuron 894 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.7108. Min Act: -0.0000

Data Index: 72988 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1085097 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.3276. Min Act: -0.0000

Data Index: 522297 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.3053. Min Act: -0.0000

Data Index: 479314 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1680. Min Act: -0.0000

Data Index: 793409 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2345. Min Act: -0.0000

Data Index: 669052 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2128. Min Act: -0.0000

Data Index: 122663 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2654. Min Act: -0.0000

Data Index: 179733 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2494. Min Act: -0.0000

Data Index: 285731 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.2236. Min Act: -0.0000

Data Index: 945171 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1457. Min Act: 0.0000

Data Index: 1174151 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1319. Min Act: 0.0000

Data Index: 805513 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0710. Min Act: 0.0000

Data Index: 412449 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1288425 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1283. Min Act: -0.0000

Data Index: 1237046 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1146. Min Act: -0.0000

Data Index: 293825 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.1104. Min Act: -0.0000

Data Index: 113805 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0924. Min Act: 0.0001

Data Index: 882888 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0228. Min Act: 0.0002

Data Index: 1326118 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 1.7108. Min Range: -1.7108

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1094121 (C4 (Web Text))

Max Activating Token Index: 342