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

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

Neuron 1202 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1554880 (Python Code)

Max Activating Token Index: 1015

Text #1

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1615916 (Python Code)

Max Activating Token Index: 867

Text #2

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1057507 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3967. Min Act: -0.0000

Data Index: 767677 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3493. Min Act: -0.0000

Data Index: 715803 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1423679 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1395079 (Python Code)

Max Activating Token Index: 377

Text #7

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3539. Min Act: -0.0000

Data Index: 275569 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3440. Min Act: -0.0000

Data Index: 661840 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1399151 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1200692 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3430. Min Act: -0.0000

Data Index: 16068 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1611231 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1066953 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1028532 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3271. Min Act: -0.0000

Data Index: 118512 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3466. Min Act: -0.0000

Data Index: 95674 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1139256 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.2912. Min Act: -0.0000

Data Index: 587625 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.4398. Min Range: -0.4398

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1427488 (Python Code)

Max Activating Token Index: 328