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

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

Neuron 1926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0458. Min Range: -5.0458

Max Act: 5.0458. Min Act: -0.0000

Data Index: 215548 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 5.0458. Min Range: -5.0458

Max Act: 4.6621. Min Act: -0.0000

Data Index: 404433 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.5422. Min Act: -0.0000

Data Index: 362120 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.9733. Min Act: -0.0000

Data Index: 286621 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.9851. Min Act: -0.0000

Data Index: 682670 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.8657. Min Act: -0.0000

Data Index: 660530 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.8250. Min Act: -0.0000

Data Index: 975331 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.9567. Min Act: -0.0000

Data Index: 951339 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.8173. Min Act: -0.0000

Data Index: 2363 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.3206. Min Act: -0.0000

Data Index: 76741 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.4415. Min Act: -0.0000

Data Index: 437541 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.4479. Min Act: -0.0000

Data Index: 759100 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.5083. Min Act: -0.0000

Data Index: 258529 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.5146. Min Act: -0.0000

Data Index: 1289516 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.3301. Min Act: -0.0000

Data Index: 1126245 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.4924. Min Act: -0.0000

Data Index: 1229175 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.5532. Min Act: -0.0000

Data Index: 179343 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.5211. Min Act: -0.0000

Data Index: 938645 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.4860. Min Act: -0.0000

Data Index: 1355809 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 5.0458. Min Range: -5.0458

Max Act: 3.2676. Min Act: -0.0000

Data Index: 278094 (C4 (Web Text))

Max Activating Token Index: 411