Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1598 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.1368. Min Act: -0.0000

Data Index: 579281 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9188. Min Act: -0.0001

Data Index: 368625 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9013. Min Act: -0.0001

Data Index: 1188099 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9584. Min Act: -0.0000

Data Index: 225305 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9111. Min Act: -0.0001

Data Index: 260264 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8864. Min Act: -0.0000

Data Index: 225431 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8735. Min Act: -0.0001

Data Index: 1022366 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1252811 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8268. Min Act: -0.0000

Data Index: 225582 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8408. Min Act: -0.0000

Data Index: 382946 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7449. Min Act: -0.0000

Data Index: 267932 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7266. Min Act: -0.0000

Data Index: 483820 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1347121 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7228. Min Act: -0.0000

Data Index: 45725 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1241345 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7049. Min Act: -0.0000

Data Index: 1235517 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7113. Min Act: -0.0000

Data Index: 182194 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6689. Min Act: -0.0001

Data Index: 523431 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6517. Min Act: -0.0000

Data Index: 979021 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6663. Min Act: -0.0000

Data Index: 491240 (C4 (Web Text))

Max Activating Token Index: 393