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

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

Neuron 783 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.3084. Min Act: -0.0000

Data Index: 289014 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1139743 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2468. Min Act: -0.0000

Data Index: 63433 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2212. Min Act: -0.0000

Data Index: 644292 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2189. Min Act: -0.0000

Data Index: 671907 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2172. Min Act: -0.0000

Data Index: 113499 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2099. Min Act: -0.0000

Data Index: 799943 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2156. Min Act: -0.0000

Data Index: 709696 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2119. Min Act: -0.0000

Data Index: 635170 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2047. Min Act: -0.0000

Data Index: 321396 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1303847 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.2174. Min Act: -0.0000

Data Index: 696675 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1980. Min Act: -0.0000

Data Index: 828233 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1225389 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1320381 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1788. Min Act: -0.0000

Data Index: 750001 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1942. Min Act: -0.0000

Data Index: 554413 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1944. Min Act: -0.0000

Data Index: 937782 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1998. Min Act: -0.0000

Data Index: 430897 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.3084. Min Range: -0.3084

Max Act: 0.1803. Min Act: -0.0000

Data Index: 404379 (C4 (Web Text))

Max Activating Token Index: 56