Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5655 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5010. Min Range: -1.5010

Max Act: 1.5010. Min Act: -0.0000

Data Index: 213155 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.5010. Min Range: -1.5010

Max Act: 1.1093. Min Act: -0.0001

Data Index: 477751 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8689. Min Act: -0.0000

Data Index: 359793 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7882. Min Act: -0.0000

Data Index: 762498 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8007. Min Act: -0.0001

Data Index: 945427 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1250595 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7433. Min Act: -0.0001

Data Index: 101961 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7371. Min Act: -0.0000

Data Index: 1071351 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7306. Min Act: -0.0000

Data Index: 166921 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7178. Min Act: -0.0000

Data Index: 496308 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6749. Min Act: -0.0000

Data Index: 685436 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7082. Min Act: -0.0000

Data Index: 986786 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6844. Min Act: -0.0000

Data Index: 750245 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7061. Min Act: -0.0001

Data Index: 472372 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7572. Min Act: -0.0000

Data Index: 132499 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1320184 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7031. Min Act: -0.0000

Data Index: 816654 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1166899 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6789. Min Act: -0.0000

Data Index: 374706 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.5010. Min Range: -1.5010

Max Act: 0.6043. Min Act: -0.0000

Data Index: 481688 (C4 (Web Text))

Max Activating Token Index: 66