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

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

Neuron 1880 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: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: -0.0001

Data Index: 124237 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1866. Min Act: -0.0001

Data Index: 1229118 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1409866 (Python Code)

Max Activating Token Index: 315

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2132. Min Act: -0.0001

Data Index: 991010 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2076. Min Act: -0.0001

Data Index: 966904 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1146842 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1982. Min Act: -0.0001

Data Index: 377400 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1168820 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1915. Min Act: -0.0001

Data Index: 22187 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1848. Min Act: -0.0001

Data Index: 165289 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1553007 (Python Code)

Max Activating Token Index: 168

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1964. Min Act: -0.0001

Data Index: 266393 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1875. Min Act: -0.0001

Data Index: 208175 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1193456 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1816. Min Act: -0.0001

Data Index: 950600 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1293102 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1875. Min Act: -0.0001

Data Index: 515047 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1861. Min Act: -0.0001

Data Index: 959328 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1962. Min Act: -0.0001

Data Index: 187182 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1873. Min Act: -0.0001

Data Index: 157726 (C4 (Web Text))

Max Activating Token Index: 260