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

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

Neuron 1086 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.3315. Min Act: -0.0001

Data Index: 1277159 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.3498. Min Act: -0.0001

Data Index: 253936 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.4758. Min Act: -0.0001

Data Index: 539187 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.4046. Min Act: -0.0001

Data Index: 254148 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.3771. Min Act: -0.0001

Data Index: 513117 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2612. Min Act: -0.0001

Data Index: 1064768 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.3309. Min Act: -0.0001

Data Index: 671834 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1246150 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2442. Min Act: -0.0001

Data Index: 904213 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2691. Min Act: -0.0001

Data Index: 991279 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2965. Min Act: -0.0001

Data Index: 397493 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1703. Min Act: -0.0001

Data Index: 901568 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2770. Min Act: -0.0001

Data Index: 528356 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.3110. Min Act: -0.0001

Data Index: 536875 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.2247. Min Act: -0.0001

Data Index: 667497 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1867. Min Act: -0.0001

Data Index: 707238 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1396. Min Act: -0.0001

Data Index: 971586 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1591. Min Act: -0.0001

Data Index: 733876 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1533. Min Act: -0.0001

Data Index: 1014488 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 1.4758. Min Range: -1.4758

Max Act: 1.1995. Min Act: -0.0001

Data Index: 518920 (C4 (Web Text))

Max Activating Token Index: 390