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

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

Neuron 478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5536. Min Range: -4.5536

Max Act: 4.5536. Min Act: -0.0000

Data Index: 724334 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.5700. Min Act: -0.0000

Data Index: 677302 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.5074. Min Act: -0.0000

Data Index: 204203 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.6629. Min Act: -0.0000

Data Index: 228391 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.5930. Min Act: -0.0000

Data Index: 1162907 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.6117. Min Act: -0.0000

Data Index: 108133 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.3157. Min Act: -0.0000

Data Index: 488852 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.3209. Min Act: -0.0000

Data Index: 131310 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.3875. Min Act: -0.0000

Data Index: 1219845 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.3655. Min Act: -0.0000

Data Index: 1206429 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 4.5536. Min Range: -4.5536

Max Act: 2.9916. Min Act: -0.0000

Data Index: 38627 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.4517. Min Act: -0.0000

Data Index: 1129960 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.5958. Min Act: -0.0000

Data Index: 716448 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.2019. Min Act: -0.0000

Data Index: 221193 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.0590. Min Act: -0.0000

Data Index: 721632 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.2050. Min Act: -0.0000

Data Index: 606486 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 4.5536. Min Range: -4.5536

Max Act: 2.9879. Min Act: -0.0000

Data Index: 1212053 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.1295. Min Act: -0.0000

Data Index: 582551 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 4.5536. Min Range: -4.5536

Max Act: 3.2526. Min Act: -0.0000

Data Index: 188332 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 4.5536. Min Range: -4.5536

Max Act: 2.9660. Min Act: -0.0000

Data Index: 223692 (C4 (Web Text))

Max Activating Token Index: 922