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

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

Neuron 4672 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: 3.1004. Min Range: -3.1004

Max Act: 3.1004. Min Act: -0.0001

Data Index: 347944 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.7306. Min Act: -0.0001

Data Index: 826798 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 3.1004. Min Range: -3.1004

Max Act: 3.0027. Min Act: -0.0001

Data Index: 1311101 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.6354. Min Act: -0.0001

Data Index: 1175131 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.9032. Min Act: -0.0001

Data Index: 1258143 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.8243. Min Act: -0.0001

Data Index: 1219974 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.7210. Min Act: -0.0001

Data Index: 1213544 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4780. Min Act: -0.0001

Data Index: 1045819 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4698. Min Act: -0.0001

Data Index: 246952 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.5299. Min Act: -0.0001

Data Index: 1206668 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4677. Min Act: -0.0001

Data Index: 844225 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4574. Min Act: -0.0001

Data Index: 214878 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.6909. Min Act: -0.0001

Data Index: 124615 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4215. Min Act: -0.0001

Data Index: 1157663 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.4870. Min Act: -0.0001

Data Index: 303683 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.1109. Min Act: -0.0001

Data Index: 253115 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.2874. Min Act: -0.0001

Data Index: 718218 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 3.1004. Min Range: -3.1004

Max Act: 1.9476. Min Act: -0.0001

Data Index: 1317157 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 3.1004. Min Range: -3.1004

Max Act: 2.3069. Min Act: -0.0001

Data Index: 413183 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 3.1004. Min Range: -3.1004

Max Act: 1.9663. Min Act: -0.0001

Data Index: 1285586 (C4 (Web Text))

Max Activating Token Index: 655