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

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

Neuron 1026 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: 1.1506. Min Range: -1.1506

Max Act: 1.1506. Min Act: -0.0000

Data Index: 880110 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.8066. Min Act: -0.0000

Data Index: 93248 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.8567. Min Act: -0.0000

Data Index: 954423 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.7615. Min Act: -0.0000

Data Index: 836965 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.7934. Min Act: -0.0001

Data Index: 81569 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1242531 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1143788 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6593. Min Act: -0.0001

Data Index: 558442 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6679. Min Act: -0.0000

Data Index: 526454 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6202. Min Act: -0.0000

Data Index: 495065 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6099. Min Act: -0.0000

Data Index: 588540 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5842. Min Act: -0.0000

Data Index: 226221 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5672. Min Act: -0.0001

Data Index: 660828 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1281975 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5544. Min Act: -0.0000

Data Index: 781737 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.6298. Min Act: -0.0000

Data Index: 807332 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5345. Min Act: -0.0000

Data Index: 392513 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5249. Min Act: -0.0001

Data Index: 908423 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.4956. Min Act: -0.0000

Data Index: 161661 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 1.1506. Min Range: -1.1506

Max Act: 0.5419. Min Act: -0.0001

Data Index: 65546 (C4 (Web Text))

Max Activating Token Index: 110