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

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

Neuron 148 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: 0.8548. Min Range: -0.8548

Max Act: 0.7371. Min Act: -0.0000

Data Index: 607094 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.8548. Min Act: -0.0000

Data Index: 881955 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6912. Min Act: -0.0000

Data Index: 65509 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6992. Min Act: -0.0000

Data Index: 775203 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6288. Min Act: -0.0000

Data Index: 989115 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.7313. Min Act: -0.0000

Data Index: 944115 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6430. Min Act: -0.0000

Data Index: 548502 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5711. Min Act: -0.0000

Data Index: 225438 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1335749 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1151195 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5424. Min Act: -0.0000

Data Index: 795199 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5522. Min Act: -0.0000

Data Index: 425924 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1127000 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.6084. Min Act: 0.0000

Data Index: 252301 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5926. Min Act: 0.0000

Data Index: 1056250 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1350670 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5442. Min Act: 0.0000

Data Index: 803376 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5564. Min Act: -0.0000

Data Index: 774834 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5756. Min Act: -0.0000

Data Index: 425161 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 0.8548. Min Range: -0.8548

Max Act: 0.5533. Min Act: -0.0000

Data Index: 8911 (C4 (Web Text))

Max Activating Token Index: 134