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

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

Neuron 3841 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: 0.4709. Min Range: -0.4709

Max Act: 0.4709. Min Act: -0.0000

Data Index: 138018 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1339596 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.3029. Min Act: -0.0000

Data Index: 410805 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2770. Min Act: -0.0000

Data Index: 54014 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1091386 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2582. Min Act: -0.0000

Data Index: 716011 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2630. Min Act: -0.0000

Data Index: 827893 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2730. Min Act: -0.0000

Data Index: 428189 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2398. Min Act: -0.0000

Data Index: 994074 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1584636 (Python Code)

Max Activating Token Index: 847

Text #10

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2268. Min Act: -0.0000

Data Index: 709193 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2241. Min Act: -0.0000

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2118. Min Act: -0.0000

Data Index: 501451 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2297. Min Act: -0.0000

Data Index: 64297 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2094. Min Act: -0.0000

Data Index: 191520 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1094929 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1262929 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1292112 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2126. Min Act: -0.0000

Data Index: 178266 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.4709. Min Range: -0.4709

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1274186 (C4 (Web Text))

Max Activating Token Index: 447