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

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

Neuron 1667 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.2071. Min Act: -0.0000

Data Index: 492688 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.2071. Min Range: -1.2071

Max Act: 1.0969. Min Act: -0.0000

Data Index: 488358 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.9002. Min Act: -0.0000

Data Index: 480054 (C4 (Web Text))

Max Activating Token Index: 988

Text #3

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1233685 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8728. Min Act: -0.0000

Data Index: 317382 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8705. Min Act: -0.0000

Data Index: 40553 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8700. Min Act: -0.0000

Data Index: 546619 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7640. Min Act: -0.0000

Data Index: 1282187 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7973. Min Act: -0.0000

Data Index: 141056 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1338233 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8213. Min Act: -0.0000

Data Index: 991752 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7788. Min Act: -0.0000

Data Index: 1172178 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8100. Min Act: -0.0000

Data Index: 322016 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7620. Min Act: -0.0000

Data Index: 508591 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.8054. Min Act: -0.0000

Data Index: 94592 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7847. Min Act: -0.0000

Data Index: 674526 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1330134 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7113. Min Act: -0.0000

Data Index: 98390 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7312. Min Act: -0.0000

Data Index: 230797 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.2071. Min Range: -1.2071

Max Act: 0.7494. Min Act: -0.0000

Data Index: 107742 (C4 (Web Text))

Max Activating Token Index: 310