Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2996 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2237. Min Act: -0.0004

Data Index: 825137 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2270. Min Act: -0.0004

Data Index: 757281 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2248. Min Act: -0.0004

Data Index: 162525 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1827. Min Act: -0.0004

Data Index: 706146 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2026. Min Act: -0.0004

Data Index: 1310515 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2027. Min Act: -0.0004

Data Index: 513671 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1677. Min Act: -0.0004

Data Index: 423145 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1909. Min Act: -0.0004

Data Index: 367888 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2247. Min Act: -0.0004

Data Index: 70782 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2034. Min Act: -0.0004

Data Index: 763800 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2235. Min Act: -0.0004

Data Index: 754738 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1503. Min Act: -0.0004

Data Index: 185042 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2050. Min Act: -0.0004

Data Index: 566713 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1901. Min Act: -0.0004

Data Index: 1706 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2251. Min Act: -0.0004

Data Index: 1084096 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1886. Min Act: -0.0004

Data Index: 615892 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1944. Min Act: -0.0004

Data Index: 1010869 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1785. Min Act: -0.0004

Data Index: 877812 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.1919. Min Act: -0.0004

Data Index: 808697 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.2321. Min Range: -0.2321

Max Act: 0.2321. Min Act: -0.0004

Data Index: 728055 (C4 (Web Text))

Max Activating Token Index: 577