Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1603 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3539. Min Act: -0.0001

Data Index: 168108 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3324. Min Act: -0.0001

Data Index: 194167 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.3243. Min Act: -0.0001

Data Index: 1126444 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2962. Min Act: -0.0001

Data Index: 824777 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2990. Min Act: -0.0001

Data Index: 411034 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2711. Min Act: -0.0001

Data Index: 581069 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2515. Min Act: -0.0001

Data Index: 119765 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2401. Min Act: -0.0001

Data Index: 1328732 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2450. Min Act: -0.0001

Data Index: 451296 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2486. Min Act: -0.0001

Data Index: 964569 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1339827 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2179. Min Act: -0.0001

Data Index: 465415 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2162. Min Act: -0.0001

Data Index: 13234 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2380. Min Act: -0.0001

Data Index: 114573 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2196. Min Act: -0.0001

Data Index: 612787 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2284. Min Act: -0.0001

Data Index: 312542 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2160. Min Act: -0.0001

Data Index: 328209 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2179. Min Act: -0.0001

Data Index: 419300 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2303. Min Act: -0.0001

Data Index: 499014 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.3539. Min Range: -0.3539

Max Act: 0.2343. Min Act: -0.0001

Data Index: 753368 (C4 (Web Text))

Max Activating Token Index: 663