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

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

Neuron 1429 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.4002. Min Act: -0.0000

Data Index: 1396262 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 1.4002. Min Range: -1.4002

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1523722 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9949. Min Act: -0.0000

Data Index: 162662 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1371921 (Python Code)

Max Activating Token Index: 358

Text #4

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1233895 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8442. Min Act: -0.0000

Data Index: 396471 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8930. Min Act: -0.0000

Data Index: 619661 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8935. Min Act: -0.0000

Data Index: 740092 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9116. Min Act: -0.0000

Data Index: 966997 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.9187. Min Act: -0.0000

Data Index: 35861 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8714. Min Act: -0.0000

Data Index: 342187 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1513477 (Python Code)

Max Activating Token Index: 440

Text #12

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8688. Min Act: -0.0000

Data Index: 891970 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8596. Min Act: -0.0000

Data Index: 457939 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8273. Min Act: -0.0000

Data Index: 490525 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1463323 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8499. Min Act: -0.0000

Data Index: 54461 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8617. Min Act: -0.0000

Data Index: 313839 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1569522 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 1.4002. Min Range: -1.4002

Max Act: 0.7437. Min Act: -0.0000

Data Index: 1411902 (Python Code)

Max Activating Token Index: 845