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

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

Neuron 4088 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1072076 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2397. Min Act: -0.0000

Data Index: 984977 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2362. Min Act: -0.0000

Data Index: 552241 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1284489 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2248. Min Act: -0.0000

Data Index: 320183 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1055557 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2332. Min Act: -0.0001

Data Index: 998409 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2369. Min Act: -0.0000

Data Index: 656903 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2281. Min Act: -0.0000

Data Index: 19803 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2332. Min Act: -0.0001

Data Index: 1067709 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2244. Min Act: -0.0000

Data Index: 519370 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2314. Min Act: -0.0001

Data Index: 616703 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2294. Min Act: -0.0001

Data Index: 781207 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2200. Min Act: -0.0001

Data Index: 91270 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2180. Min Act: -0.0001

Data Index: 175854 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2107. Min Act: -0.0001

Data Index: 15122 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2127. Min Act: -0.0001

Data Index: 994926 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2208. Min Act: -0.0000

Data Index: 971038 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2124. Min Act: -0.0001

Data Index: 1075888 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.2569. Min Range: -0.2569

Max Act: 0.2117. Min Act: -0.0000

Data Index: 248121 (C4 (Web Text))

Max Activating Token Index: 869