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

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

Neuron 4663 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2472. Min Act: -0.0002

Data Index: 272169 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2735. Min Act: -0.0002

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2350. Min Act: -0.0002

Data Index: 163594 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2361. Min Act: -0.0002

Data Index: 1499262 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2417. Min Act: -0.0002

Data Index: 1151354 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2381. Min Act: -0.0002

Data Index: 982114 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2602. Min Act: -0.0002

Data Index: 213582 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2239. Min Act: -0.0002

Data Index: 407443 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2523. Min Act: -0.0002

Data Index: 194463 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2650. Min Act: -0.0002

Data Index: 75557 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2357. Min Act: -0.0002

Data Index: 814838 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2600. Min Act: -0.0002

Data Index: 1238698 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2120. Min Act: -0.0002

Data Index: 982626 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2393. Min Act: -0.0002

Data Index: 1641928 (Python Code)

Max Activating Token Index: 204

Text #14

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2282. Min Act: -0.0002

Data Index: 393493 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2453. Min Act: -0.0002

Data Index: 1502589 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2250. Min Act: -0.0002

Data Index: 1371957 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2134. Min Act: -0.0002

Data Index: 1337228 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2229. Min Act: -0.0002

Data Index: 1482840 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.2735. Min Range: -0.2735

Max Act: 0.2227. Min Act: -0.0002

Data Index: 1114184 (C4 (Web Text))

Max Activating Token Index: 57