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

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

Neuron 4882 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.9427. Min Act: -0.0000

Data Index: 624740 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.7982. Min Act: -0.0000

Data Index: 829643 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.6686. Min Act: -0.0000

Data Index: 337683 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.2305. Min Act: -0.0000

Data Index: 1159917 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.3349. Min Act: -0.0000

Data Index: 950790 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.5195. Min Act: -0.0000

Data Index: 737678 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.5082. Min Act: -0.0000

Data Index: 385948 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1125023 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.3912. Min Act: -0.0000

Data Index: 67622 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.4920. Min Act: -0.0000

Data Index: 766136 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.0134. Min Act: -0.0000

Data Index: 834590 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.1067. Min Act: -0.0000

Data Index: 366797 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.0753. Min Act: -0.0000

Data Index: 642524 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.1578. Min Act: -0.0000

Data Index: 561576 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.1500. Min Act: -0.0000

Data Index: 408391 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.1284. Min Act: -0.0000

Data Index: 348965 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.1098. Min Act: -0.0000

Data Index: 973514 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.0808. Min Act: -0.0000

Data Index: 1029778 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 2.9427. Min Range: -2.9427

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1246539 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 2.9427. Min Range: -2.9427

Max Act: 1.9259. Min Act: -0.0000

Data Index: 943790 (C4 (Web Text))

Max Activating Token Index: 965