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

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

Neuron 978 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2664. Min Act: -0.0000

Data Index: 425289 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2392. Min Act: -0.0000

Data Index: 343869 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2280. Min Act: -0.0000

Data Index: 994989 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2255. Min Act: -0.0000

Data Index: 686337 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2217. Min Act: -0.0000

Data Index: 458600 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2190. Min Act: -0.0000

Data Index: 342001 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2233. Min Act: -0.0000

Data Index: 492242 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2075. Min Act: -0.0000

Data Index: 946620 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1968. Min Act: -0.0000

Data Index: 855876 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1255801 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1950. Min Act: -0.0000

Data Index: 426001 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1904. Min Act: -0.0000

Data Index: 724373 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1827. Min Act: -0.0000

Data Index: 672410 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1930. Min Act: -0.0000

Data Index: 179515 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1919. Min Act: -0.0000

Data Index: 167983 (C4 (Web Text))

Max Activating Token Index: 994

Text #15

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1931. Min Act: -0.0000

Data Index: 502336 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1904. Min Act: -0.0000

Data Index: 614552 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1849. Min Act: -0.0000

Data Index: 858749 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1154059 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1835. Min Act: -0.0000

Data Index: 781860 (C4 (Web Text))

Max Activating Token Index: 794