Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3105 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.3418. Min Act: -0.0000

Data Index: 601507 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1556150 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1640244 (Python Code)

Max Activating Token Index: 527

Text #3

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2821. Min Act: -0.0000

Data Index: 803705 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2550. Min Act: -0.0000

Data Index: 467178 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2543. Min Act: -0.0000

Data Index: 102924 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2519. Min Act: -0.0000

Data Index: 842185 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.0099. Min Act: -0.0000

Data Index: 1488111 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2420. Min Act: -0.0000

Data Index: 183504 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1141912 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2378. Min Act: -0.0000

Data Index: 765830 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2384. Min Act: -0.0000

Data Index: 560972 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1246194 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2140. Min Act: -0.0000

Data Index: 639981 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2090. Min Act: -0.0000

Data Index: 893595 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2143. Min Act: -0.0000

Data Index: 442821 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2302. Min Act: -0.0000

Data Index: 813255 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1172256 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.2080. Min Act: -0.0000

Data Index: 850647 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.3418. Min Range: -0.3418

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1635814 (Python Code)

Max Activating Token Index: 672