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

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

Neuron 3086 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: 0.7289. Min Range: -0.7289

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1525071 (Python Code)

Max Activating Token Index: 988

Text #1

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1636179 (Python Code)

Max Activating Token Index: 339

Text #2

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1600325 (Python Code)

Max Activating Token Index: 791

Text #3

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1512225 (Python Code)

Max Activating Token Index: 285

Text #4

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1579528 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1570281 (Python Code)

Max Activating Token Index: 780

Text #6

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1379206 (Python Code)

Max Activating Token Index: 402

Text #7

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1402959 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1539813 (Python Code)

Max Activating Token Index: 650

Text #9

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1526471 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1367429 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1458356 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5630. Min Act: -0.0000

Data Index: 1398019 (Python Code)

Max Activating Token Index: 322

Text #13

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1492481 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1415324 (Python Code)

Max Activating Token Index: 391

Text #15

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1490315 (Python Code)

Max Activating Token Index: 934

Text #16

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1422798 (Python Code)

Max Activating Token Index: 971

Text #17

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1624745 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4947. Min Act: -0.0000

Data Index: 1599158 (Python Code)

Max Activating Token Index: 498

Text #19

Max Range: 0.7289. Min Range: -0.7289

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1362892 (Python Code)

Max Activating Token Index: 476