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

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

Neuron 2897 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1262358 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.5192. Min Act: -0.0000

Data Index: 645025 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.4080. Min Act: -0.0000

Data Index: 510691 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.4193. Min Act: -0.0000

Data Index: 6448 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.4003. Min Act: -0.0000

Data Index: 337283 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3825. Min Act: -0.0000

Data Index: 643472 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1189871 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3679. Min Act: -0.0000

Data Index: 830266 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1207730 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3499. Min Act: -0.0000

Data Index: 696904 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3352. Min Act: -0.0000

Data Index: 164946 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3436. Min Act: -0.0000

Data Index: 412966 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3490. Min Act: -0.0000

Data Index: 769291 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3364. Min Act: -0.0000

Data Index: 11384 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1123396 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1222753 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1282032 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3114. Min Act: -0.0000

Data Index: 281819 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.3018. Min Act: -0.0000

Data Index: 991760 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.8032. Min Range: -0.8032

Max Act: 0.2957. Min Act: -0.0000

Data Index: 680050 (C4 (Web Text))

Max Activating Token Index: 900