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

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

Neuron 2154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0767. Min Act: -0.0002

Data Index: 1095108 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0204. Min Act: -0.0002

Data Index: 1077122 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 1.0767. Min Range: -1.0767

Max Act: 1.0029. Min Act: -0.0002

Data Index: 1076305 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9469. Min Act: -0.0002

Data Index: 154818 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8893. Min Act: -0.0002

Data Index: 31987 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8819. Min Act: -0.0002

Data Index: 783985 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.9028. Min Act: -0.0002

Data Index: 289003 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8627. Min Act: -0.0001

Data Index: 229418 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8344. Min Act: -0.0002

Data Index: 63151 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8161. Min Act: -0.0002

Data Index: 1255696 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8151. Min Act: -0.0002

Data Index: 653070 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8313. Min Act: -0.0002

Data Index: 480083 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8026. Min Act: -0.0002

Data Index: 781718 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.7990. Min Act: -0.0002

Data Index: 788113 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8277. Min Act: -0.0002

Data Index: 713923 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8478. Min Act: -0.0002

Data Index: 162386 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8102. Min Act: -0.0002

Data Index: 169051 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.8343. Min Act: -0.0002

Data Index: 998496 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.7775. Min Act: -0.0002

Data Index: 709279 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 1.0767. Min Range: -1.0767

Max Act: 0.7453. Min Act: -0.0002

Data Index: 660258 (C4 (Web Text))

Max Activating Token Index: 246