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

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

Neuron 4743 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: 2.8774. Min Range: -2.8774

Max Act: 2.8774. Min Act: -0.0000

Data Index: 834762 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 2.8774. Min Range: -2.8774

Max Act: 2.6116. Min Act: -0.0000

Data Index: 1233561 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7706. Min Act: -0.0000

Data Index: 1424641 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7850. Min Act: -0.0000

Data Index: 1569549 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6312. Min Act: -0.0000

Data Index: 1501309 (Python Code)

Max Activating Token Index: 245

Text #5

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7601. Min Act: -0.0000

Data Index: 327655 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.8739. Min Act: -0.0000

Data Index: 795373 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1589406 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6711. Min Act: -0.0000

Data Index: 1570829 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7326. Min Act: -0.0000

Data Index: 1431343 (Python Code)

Max Activating Token Index: 381

Text #10

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6898. Min Act: -0.0000

Data Index: 1420829 (Python Code)

Max Activating Token Index: 209

Text #11

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6788. Min Act: -0.0000

Data Index: 1486358 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1389344 (Python Code)

Max Activating Token Index: 443

Text #13

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.5983. Min Act: -0.0000

Data Index: 447714 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6976. Min Act: -0.0000

Data Index: 1474572 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.7097. Min Act: -0.0000

Data Index: 1457632 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.5270. Min Act: -0.0000

Data Index: 437108 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.5872. Min Act: -0.0000

Data Index: 1380100 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.4918. Min Act: -0.0000

Data Index: 1624749 (Python Code)

Max Activating Token Index: 308

Text #19

Max Range: 2.8774. Min Range: -2.8774

Max Act: 1.6194. Min Act: -0.0000

Data Index: 1603606 (Python Code)

Max Activating Token Index: 898