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

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

Neuron 731 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2277. Min Act: -0.0001

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1892. Min Act: -0.0001

Data Index: 165744 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2170. Min Act: -0.0001

Data Index: 1185742 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.2004. Min Act: -0.0001

Data Index: 158263 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1909. Min Act: -0.0001

Data Index: 73093 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1952. Min Act: -0.0001

Data Index: 929156 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1297549 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1920. Min Act: -0.0001

Data Index: 257558 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1912. Min Act: -0.0001

Data Index: 1111074 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1902. Min Act: -0.0001

Data Index: 162377 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1002693 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1872. Min Act: -0.0001

Data Index: 551575 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1939. Min Act: -0.0001

Data Index: 358241 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1866. Min Act: -0.0001

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1298159 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1791. Min Act: -0.0001

Data Index: 101364 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1787. Min Act: -0.0001

Data Index: 343957 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1341459 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1708. Min Act: -0.0001

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.2277. Min Range: -0.2277

Max Act: 0.1825. Min Act: -0.0001

Data Index: 104844 (C4 (Web Text))

Max Activating Token Index: 928