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

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

Neuron 475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0614. Min Act: -0.0002

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0505. Min Act: -0.0002

Data Index: 442563 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1072228 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0527. Min Act: -0.0002

Data Index: 718006 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0492. Min Act: -0.0002

Data Index: 799327 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0464. Min Act: -0.0002

Data Index: 654543 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1249528 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1105756 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0437. Min Act: -0.0002

Data Index: 263486 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1271750 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0378. Min Act: -0.0002

Data Index: 1164454 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0389. Min Act: -0.0002

Data Index: 276139 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0389. Min Act: -0.0002

Data Index: 713820 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0381. Min Act: -0.0002

Data Index: 161109 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0388. Min Act: -0.0002

Data Index: 89472 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1183022 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0376. Min Act: -0.0002

Data Index: 1234503 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0373. Min Act: -0.0002

Data Index: 905379 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0374. Min Act: -0.0002

Data Index: 1134400 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.0614. Min Range: -0.0614

Max Act: 0.0375. Min Act: -0.0002

Data Index: 166390 (C4 (Web Text))

Max Activating Token Index: 708