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

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

Neuron 2036 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: 0.3779. Min Range: -0.3779

Max Act: 0.3779. Min Act: -0.0001

Data Index: 277392 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3425. Min Act: -0.0000

Data Index: 924196 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3656. Min Act: -0.0001

Data Index: 873912 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3379. Min Act: -0.0001

Data Index: 994898 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3163. Min Act: -0.0001

Data Index: 788349 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1343333 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3080. Min Act: -0.0001

Data Index: 282067 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3127. Min Act: -0.0000

Data Index: 352342 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3139. Min Act: -0.0000

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3010. Min Act: -0.0001

Data Index: 405151 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1009288 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2968. Min Act: -0.0000

Data Index: 809129 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2932. Min Act: -0.0001

Data Index: 323289 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3081. Min Act: -0.0000

Data Index: 885421 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2934. Min Act: -0.0001

Data Index: 384858 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3133. Min Act: -0.0001

Data Index: 1288871 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.3012. Min Act: -0.0001

Data Index: 173792 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2917. Min Act: -0.0001

Data Index: 1254400 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2912. Min Act: -0.0000

Data Index: 151313 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.3779. Min Range: -0.3779

Max Act: 0.2998. Min Act: -0.0000

Data Index: 971513 (C4 (Web Text))

Max Activating Token Index: 66