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

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

Neuron 3085 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.8860. Min Act: -0.0000

Data Index: 676603 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.7990. Min Act: -0.0000

Data Index: 602277 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.7019. Min Act: -0.0000

Data Index: 955051 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.5758. Min Act: 0.0000

Data Index: 729869 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.0978. Min Act: -0.0000

Data Index: 1271995 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.5159. Min Act: -0.0000

Data Index: 639114 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.8272. Min Act: -0.0000

Data Index: 1064237 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.3567. Min Act: -0.0000

Data Index: 956976 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 5.8860. Min Range: -5.8860

Max Act: 5.1073. Min Act: -0.0000

Data Index: 113380 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.7023. Min Act: -0.0000

Data Index: 955325 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.8490. Min Act: -0.0000

Data Index: 239769 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.7378. Min Act: -0.0000

Data Index: 376796 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.7349. Min Act: -0.0000

Data Index: 554054 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.4831. Min Act: -0.0000

Data Index: 1320934 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.4061. Min Act: -0.0000

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 5.8860. Min Range: -5.8860

Max Act: 3.9559. Min Act: -0.0000

Data Index: 1253266 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 5.8860. Min Range: -5.8860

Max Act: 4.0205. Min Act: -0.0000

Data Index: 1305836 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 5.8860. Min Range: -5.8860

Max Act: 3.8297. Min Act: -0.0000

Data Index: 341980 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 5.8860. Min Range: -5.8860

Max Act: 3.9835. Min Act: -0.0000

Data Index: 292635 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 5.8860. Min Range: -5.8860

Max Act: 3.9563. Min Act: -0.0000

Data Index: 955847 (C4 (Web Text))

Max Activating Token Index: 29