Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3634 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6772. Min Act: -0.0000

Data Index: 957346 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6845. Min Act: -0.0000

Data Index: 496932 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6765. Min Act: -0.0000

Data Index: 479965 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1041695 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6233. Min Act: -0.0000

Data Index: 338538 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1125762 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6176. Min Act: -0.0000

Data Index: 529839 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1104107 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6278. Min Act: -0.0000

Data Index: 494853 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6776. Min Act: -0.0001

Data Index: 1284188 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6487. Min Act: -0.0000

Data Index: 626875 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5702. Min Act: -0.0000

Data Index: 229191 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1136289 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5886. Min Act: -0.0000

Data Index: 395211 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.5999. Min Act: -0.0000

Data Index: 792793 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6249. Min Act: -0.0001

Data Index: 706474 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6201. Min Act: -0.0000

Data Index: 376412 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6037. Min Act: -0.0000

Data Index: 976913 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6568. Min Act: -0.0000

Data Index: 595987 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.7261. Min Range: -0.7261

Max Act: 0.6140. Min Act: -0.0000

Data Index: 151458 (C4 (Web Text))

Max Activating Token Index: 120