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

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

Neuron 484 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.4516. Min Act: -0.0000

Data Index: 609515 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.2769. Min Act: -0.0000

Data Index: 208587 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.2090. Min Act: -0.0000

Data Index: 230096 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1398. Min Act: -0.0000

Data Index: 1179801 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.2469. Min Act: -0.0000

Data Index: 93837 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0102. Min Act: -0.0000

Data Index: 792504 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1482. Min Act: -0.0000

Data Index: 785933 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9198. Min Act: -0.0000

Data Index: 536980 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1504. Min Act: -0.0000

Data Index: 310996 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9767. Min Act: -0.0000

Data Index: 464580 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0722. Min Act: -0.0000

Data Index: 1249159 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0951. Min Act: -0.0000

Data Index: 389925 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.1569. Min Act: -0.0000

Data Index: 1009715 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0048. Min Act: -0.0000

Data Index: 1328018 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0983. Min Act: -0.0000

Data Index: 1022233 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0665. Min Act: -0.0000

Data Index: 448511 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0717. Min Act: -0.0000

Data Index: 416530 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.8426. Min Act: -0.0000

Data Index: 294198 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 2.4516. Min Range: -2.4516

Max Act: 2.0544. Min Act: -0.0000

Data Index: 1257949 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 2.4516. Min Range: -2.4516

Max Act: 1.9465. Min Act: -0.0000

Data Index: 422305 (C4 (Web Text))

Max Activating Token Index: 1022