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

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

Neuron 1234 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1964. Min Act: -0.0001

Data Index: 229644 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1089720 (C4 (Web Text))

Max Activating Token Index: 840

Text #2

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1862. Min Act: -0.0001

Data Index: 544548 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1774. Min Act: -0.0001

Data Index: 912585 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1660. Min Act: -0.0001

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1633. Min Act: -0.0001

Data Index: 68098 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1623. Min Act: -0.0001

Data Index: 244726 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1662. Min Act: -0.0001

Data Index: 999444 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1572. Min Act: -0.0001

Data Index: 1150162 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1561. Min Act: -0.0001

Data Index: 867774 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1531. Min Act: -0.0001

Data Index: 1014260 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1464. Min Act: -0.0001

Data Index: 779375 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1328533 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1454. Min Act: -0.0001

Data Index: 56850 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1407. Min Act: -0.0001

Data Index: 643748 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1404. Min Act: -0.0001

Data Index: 484602 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1512. Min Act: -0.0001

Data Index: 355855 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1438. Min Act: -0.0001

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1227290 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1964. Min Range: -0.1964

Max Act: 0.1478. Min Act: -0.0001

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 395