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

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

Neuron 1705 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1378. Min Range: -1.1378

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1518137 (Python Code)

Max Activating Token Index: 883

Text #1

Max Range: 1.1378. Min Range: -1.1378

Max Act: 1.0870. Min Act: -0.0000

Data Index: 53665 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1576275 (Python Code)

Max Activating Token Index: 631

Text #3

Max Range: 1.1378. Min Range: -1.1378

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1453399 (Python Code)

Max Activating Token Index: 969

Text #4

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1401176 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1560834 (Python Code)

Max Activating Token Index: 211

Text #6

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1525529 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.8035. Min Act: -0.0000

Data Index: 1546990 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1337660 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1442706 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.6097. Min Act: -0.0000

Data Index: 998608 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1275569 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.5423. Min Act: -0.0000

Data Index: 98587 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.5043. Min Act: -0.0000

Data Index: 703738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1481786 (Python Code)

Max Activating Token Index: 522

Text #15

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.5162. Min Act: -0.0000

Data Index: 193565 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.4979. Min Act: -0.0000

Data Index: 562592 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.4570. Min Act: -0.0000

Data Index: 910792 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.4454. Min Act: -0.0000

Data Index: 62467 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.1378. Min Range: -1.1378

Max Act: 0.4559. Min Act: -0.0000

Data Index: 87874 (C4 (Web Text))

Max Activating Token Index: 710