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

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

Neuron 4813 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2466. Min Act: -0.0002

Data Index: 1135819 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2309. Min Act: -0.0002

Data Index: 1286012 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2280. Min Act: -0.0002

Data Index: 199628 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2282. Min Act: -0.0002

Data Index: 532592 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2210. Min Act: -0.0002

Data Index: 295648 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1021171 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2063. Min Act: -0.0002

Data Index: 877678 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2059. Min Act: -0.0002

Data Index: 1585535 (Python Code)

Max Activating Token Index: 407

Text #8

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2083. Min Act: -0.0002

Data Index: 1166868 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2085. Min Act: -0.0002

Data Index: 736567 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1947. Min Act: -0.0002

Data Index: 607504 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1983. Min Act: -0.0002

Data Index: 82064 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.2092. Min Act: -0.0002

Data Index: 1168254 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1947. Min Act: -0.0002

Data Index: 1226550 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1855. Min Act: -0.0002

Data Index: 1182109 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1913. Min Act: -0.0002

Data Index: 680309 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1905. Min Act: -0.0002

Data Index: 346444 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1835. Min Act: -0.0002

Data Index: 956317 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1895. Min Act: -0.0002

Data Index: 288450 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.2466. Min Range: -0.2466

Max Act: 0.1856. Min Act: -0.0002

Data Index: 18660 (C4 (Web Text))

Max Activating Token Index: 321