Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3241 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0816. Min Range: -1.0816

Max Act: 1.0816. Min Act: -0.0001

Data Index: 903491 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8269. Min Act: -0.0001

Data Index: 1231921 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8947. Min Act: -0.0001

Data Index: 741115 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8398. Min Act: -0.0001

Data Index: 635316 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8317. Min Act: -0.0001

Data Index: 640407 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8526. Min Act: -0.0001

Data Index: 190804 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8490. Min Act: -0.0001

Data Index: 912460 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8594. Min Act: -0.0001

Data Index: 962511 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8063. Min Act: -0.0001

Data Index: 966078 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7985. Min Act: -0.0001

Data Index: 909958 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7951. Min Act: -0.0001

Data Index: 1000586 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8214. Min Act: -0.0001

Data Index: 833312 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7873. Min Act: -0.0001

Data Index: 260957 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7878. Min Act: -0.0001

Data Index: 271411 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8088. Min Act: -0.0001

Data Index: 855444 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7551. Min Act: -0.0001

Data Index: 257797 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8296. Min Act: -0.0001

Data Index: 608982 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1251518 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.8109. Min Act: -0.0001

Data Index: 954837 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 1.0816. Min Range: -1.0816

Max Act: 0.7362. Min Act: -0.0001

Data Index: 131715 (C4 (Web Text))

Max Activating Token Index: 731