Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5116 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3009. Min Act: -0.0001

Data Index: 615468 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0001

Data Index: 568104 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2728. Min Act: -0.0001

Data Index: 424130 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2647. Min Act: -0.0001

Data Index: 351174 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2366. Min Act: -0.0001

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2342. Min Act: -0.0001

Data Index: 232537 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2321. Min Act: -0.0000

Data Index: 732530 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2275. Min Act: -0.0000

Data Index: 406529 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2160. Min Act: -0.0001

Data Index: 704201 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2200. Min Act: -0.0001

Data Index: 594552 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2184. Min Act: -0.0001

Data Index: 1275367 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2019. Min Act: -0.0001

Data Index: 971165 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2271. Min Act: -0.0001

Data Index: 328955 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2082. Min Act: -0.0001

Data Index: 226727 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2097. Min Act: -0.0001

Data Index: 65050 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2070. Min Act: -0.0000

Data Index: 787933 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1208526 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1959. Min Act: -0.0001

Data Index: 483222 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2007. Min Act: -0.0001

Data Index: 1271507 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2086. Min Act: -0.0001

Data Index: 823614 (C4 (Web Text))

Max Activating Token Index: 460