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

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

Neuron 4839 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: 1.8812. Min Range: -1.8812

Max Act: 1.8812. Min Act: -0.0000

Data Index: 606206 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.7514. Min Act: -0.0000

Data Index: 122107 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.6650. Min Act: -0.0000

Data Index: 82755 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.6147. Min Act: -0.0000

Data Index: 497796 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5614. Min Act: -0.0000

Data Index: 872111 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1310322 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5191. Min Act: -0.0000

Data Index: 891833 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5534. Min Act: -0.0000

Data Index: 1297837 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3997. Min Act: -0.0000

Data Index: 397371 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.5138. Min Act: -0.0000

Data Index: 748077 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3540. Min Act: -0.0000

Data Index: 89879 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.4323. Min Act: -0.0000

Data Index: 167417 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.4009. Min Act: -0.0000

Data Index: 875904 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3604. Min Act: -0.0000

Data Index: 146410 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2951. Min Act: -0.0000

Data Index: 526084 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2804. Min Act: -0.0000

Data Index: 888460 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.2540. Min Act: -0.0000

Data Index: 661989 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.4435. Min Act: -0.0000

Data Index: 100855 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3473. Min Act: -0.0000

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.8812. Min Range: -1.8812

Max Act: 1.3763. Min Act: -0.0000

Data Index: 761832 (C4 (Web Text))

Max Activating Token Index: 59