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

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

Neuron 2758 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: 0.6378. Min Range: -0.6378

Max Act: 0.6296. Min Act: -0.0000

Data Index: 1656026 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1075660 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5922. Min Act: -0.0000

Data Index: 138189 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5746. Min Act: -0.0000

Data Index: 176980 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1434314 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5192. Min Act: -0.0000

Data Index: 153084 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1596804 (Python Code)

Max Activating Token Index: 397

Text #7

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4848. Min Act: -0.0000

Data Index: 888184 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4646. Min Act: -0.0000

Data Index: 770213 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4800. Min Act: -0.0000

Data Index: 554496 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1418062 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4890. Min Act: -0.0000

Data Index: 976768 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1346036 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4783. Min Act: -0.0000

Data Index: 195052 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1505040 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4396. Min Act: -0.0000

Data Index: 1572935 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4042. Min Act: -0.0000

Data Index: 1492170 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4261. Min Act: -0.0000

Data Index: 214290 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4104. Min Act: -0.0000

Data Index: 1554087 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 0.6378. Min Range: -0.6378

Max Act: 0.4204. Min Act: -0.0000

Data Index: 30711 (C4 (Web Text))

Max Activating Token Index: 449