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

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

Neuron 3157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.4020. Min Act: -0.0000

Data Index: 1371194 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.0355. Min Act: -0.0000

Data Index: 240765 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.0415. Min Act: -0.0000

Data Index: 635747 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.8741. Min Act: -0.0000

Data Index: 288881 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.9350. Min Act: -0.0000

Data Index: 1538204 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.8985. Min Act: -0.0000

Data Index: 135462 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.9142. Min Act: -0.0000

Data Index: 1444141 (Python Code)

Max Activating Token Index: 581

Text #7

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.0111. Min Act: -0.0000

Data Index: 216616 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.9098. Min Act: -0.0000

Data Index: 693742 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.1988. Min Act: -0.0000

Data Index: 1428705 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 2.4020. Min Range: -2.4020

Max Act: 2.0121. Min Act: -0.0000

Data Index: 666962 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.8857. Min Act: -0.0000

Data Index: 712429 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.5726. Min Act: -0.0000

Data Index: 848256 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.8523. Min Act: -0.0000

Data Index: 310580 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.7696. Min Act: -0.0000

Data Index: 755175 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.9153. Min Act: -0.0000

Data Index: 1635738 (Python Code)

Max Activating Token Index: 978

Text #16

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1560044 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.7419. Min Act: -0.0001

Data Index: 80381 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.7272. Min Act: -0.0000

Data Index: 1269845 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 2.4020. Min Range: -2.4020

Max Act: 1.9152. Min Act: -0.0000

Data Index: 1136746 (C4 (Web Text))

Max Activating Token Index: 721