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

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

Neuron 5544 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3767. Min Range: -4.3767

Max Act: 4.3767. Min Act: -0.0000

Data Index: 1215345 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.8649. Min Act: -0.0000

Data Index: 1341198 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.2110. Min Act: -0.0000

Data Index: 905014 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.8206. Min Act: -0.0000

Data Index: 1266201 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.4263. Min Act: -0.0000

Data Index: 95451 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.5787. Min Act: -0.0000

Data Index: 715239 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.6059. Min Act: -0.0000

Data Index: 1298883 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.5810. Min Act: -0.0000

Data Index: 47837 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.4552. Min Act: -0.0000

Data Index: 875778 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.6920. Min Act: -0.0000

Data Index: 976404 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.0310. Min Act: -0.0000

Data Index: 806919 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.5888. Min Act: -0.0000

Data Index: 1113283 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.9743. Min Act: -0.0000

Data Index: 502598 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.0289. Min Act: -0.0000

Data Index: 894430 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.3051. Min Act: -0.0000

Data Index: 443368 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.1332. Min Act: -0.0000

Data Index: 120367 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 4.3767. Min Range: -4.3767

Max Act: 3.0733. Min Act: -0.0000

Data Index: 440498 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.9494. Min Act: -0.0000

Data Index: 88322 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.8707. Min Act: -0.0000

Data Index: 433199 (C4 (Web Text))

Max Activating Token Index: 110

Text #19

Max Range: 4.3767. Min Range: -4.3767

Max Act: 2.6984. Min Act: -0.0000

Data Index: 296647 (C4 (Web Text))

Max Activating Token Index: 473