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

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

Neuron 2349 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.3038. Min Act: -0.0001

Data Index: 176891 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2504. Min Act: -0.0000

Data Index: 347310 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1062736 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1176050 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2509. Min Act: -0.0000

Data Index: 1032550 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1142810 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2069. Min Act: -0.0001

Data Index: 636694 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2054. Min Act: -0.0001

Data Index: 407744 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1819. Min Act: -0.0000

Data Index: 692398 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1072925 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1062193 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2004. Min Act: -0.0001

Data Index: 544048 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1859. Min Act: -0.0000

Data Index: 541917 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1801. Min Act: -0.0001

Data Index: 982000 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1914. Min Act: -0.0000

Data Index: 318773 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1310620 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1894. Min Act: -0.0000

Data Index: 728027 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1991. Min Act: -0.0001

Data Index: 191014 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.3038. Min Range: -0.3038

Max Act: 0.1882. Min Act: -0.0000

Data Index: 214051 (C4 (Web Text))

Max Activating Token Index: 574