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

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

Neuron 5906 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.7687. Min Act: -0.0000

Data Index: 76794 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.6804. Min Act: -0.0000

Data Index: 529025 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5788. Min Act: -0.0000

Data Index: 746418 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.5126. Min Act: -0.0000

Data Index: 471247 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1297070 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4932. Min Act: -0.0000

Data Index: 101411 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1193184 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4639. Min Act: -0.0000

Data Index: 71542 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4649. Min Act: 0.0000

Data Index: 1275394 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4493. Min Act: 0.0000

Data Index: 741871 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4767. Min Act: 0.0001

Data Index: 1319480 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4455. Min Act: 0.0000

Data Index: 920468 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4244. Min Act: -0.0000

Data Index: 192742 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4272. Min Act: -0.0000

Data Index: 1136303 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4240. Min Act: -0.0000

Data Index: 565148 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4173. Min Act: -0.0000

Data Index: 654008 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1091267 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4109. Min Act: -0.0000

Data Index: 411777 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.4013. Min Act: 0.0000

Data Index: 1301246 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.7687. Min Range: -0.7687

Max Act: 0.3904. Min Act: -0.0000

Data Index: 161341 (C4 (Web Text))

Max Activating Token Index: 722