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

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

Neuron 3012 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: 0.2309. Min Range: -0.2309

Max Act: 0.2135. Min Act: -0.0001

Data Index: 482208 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1275088 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2309. Min Act: -0.0001

Data Index: 801016 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1881. Min Act: -0.0000

Data Index: 650095 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2213. Min Act: -0.0001

Data Index: 324138 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2073. Min Act: -0.0000

Data Index: 884934 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2048. Min Act: -0.0001

Data Index: 637526 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1969. Min Act: -0.0001

Data Index: 389113 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1944. Min Act: -0.0001

Data Index: 1064342 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1348461 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1864. Min Act: -0.0001

Data Index: 708064 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1994. Min Act: -0.0001

Data Index: 43710 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1850. Min Act: -0.0000

Data Index: 170311 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1807. Min Act: -0.0001

Data Index: 957094 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1629. Min Act: -0.0001

Data Index: 188471 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1311782 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1652. Min Act: -0.0000

Data Index: 186790 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1646. Min Act: -0.0001

Data Index: 391164 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1635. Min Act: -0.0000

Data Index: 128227 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1211996 (C4 (Web Text))

Max Activating Token Index: 87