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

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

Neuron 4448 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: 0.7883. Min Range: -0.7883

Max Act: 0.7883. Min Act: -0.0001

Data Index: 466489 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6761. Min Act: -0.0001

Data Index: 192391 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.7058. Min Act: -0.0000

Data Index: 347051 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6521. Min Act: -0.0000

Data Index: 754087 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1226075 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6670. Min Act: -0.0001

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6594. Min Act: -0.0000

Data Index: 775060 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1102961 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6810. Min Act: -0.0001

Data Index: 495044 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5438. Min Act: -0.0001

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5935. Min Act: -0.0001

Data Index: 1051709 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5320. Min Act: -0.0001

Data Index: 806118 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5659. Min Act: -0.0001

Data Index: 158581 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.6240. Min Act: -0.0001

Data Index: 976853 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5388. Min Act: -0.0000

Data Index: 340568 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1303802 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5150. Min Act: -0.0001

Data Index: 1173193 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5155. Min Act: -0.0001

Data Index: 966165 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5692. Min Act: -0.0001

Data Index: 540515 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.7883. Min Range: -0.7883

Max Act: 0.5311. Min Act: -0.0001

Data Index: 621868 (C4 (Web Text))

Max Activating Token Index: 918