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

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

Neuron 4407 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0952. Min Range: -2.0952

Max Act: 2.0952. Min Act: -0.0000

Data Index: 1603564 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.9068. Min Act: -0.0000

Data Index: 601436 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.8534. Min Act: -0.0000

Data Index: 1357305 (C4 (Web Text))

Max Activating Token Index: 318

Text #3

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1531675 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1359889 (Python Code)

Max Activating Token Index: 731

Text #5

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.4607. Min Act: -0.0000

Data Index: 1358205 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.6260. Min Act: -0.0000

Data Index: 817636 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.4845. Min Act: -0.0000

Data Index: 363595 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1239632 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.2473. Min Act: -0.0000

Data Index: 443676 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.4611. Min Act: -0.0000

Data Index: 348890 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3732. Min Act: -0.0000

Data Index: 176450 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.4340. Min Act: -0.0000

Data Index: 950848 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1272760 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1242887 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3547. Min Act: -0.0000

Data Index: 1526417 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1351598 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.3083. Min Act: -0.0000

Data Index: 1458604 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1437175 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 2.0952. Min Range: -2.0952

Max Act: 1.2986. Min Act: -0.0000

Data Index: 179341 (C4 (Web Text))

Max Activating Token Index: 177