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

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

Neuron 102 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: 1.4430. Min Range: -1.4430

Max Act: 1.4430. Min Act: -0.0001

Data Index: 978154 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3208. Min Act: -0.0001

Data Index: 122313 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1305274 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2333. Min Act: -0.0001

Data Index: 561202 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1741. Min Act: -0.0001

Data Index: 1125925 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.2559. Min Act: -0.0000

Data Index: 1175496 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1555. Min Act: -0.0001

Data Index: 506543 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1455. Min Act: -0.0000

Data Index: 828427 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1873. Min Act: -0.0001

Data Index: 358105 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1207. Min Act: -0.0001

Data Index: 1093016 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0604. Min Act: -0.0001

Data Index: 66295 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1526. Min Act: -0.0001

Data Index: 1633766 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.1005. Min Act: -0.0001

Data Index: 1034838 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0800. Min Act: -0.0001

Data Index: 29628 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0986. Min Act: -0.0000

Data Index: 353096 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 1.4430. Min Range: -1.4430

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1057897 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0380. Min Act: -0.0001

Data Index: 486643 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0507. Min Act: -0.0001

Data Index: 77131 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0256. Min Act: -0.0001

Data Index: 712723 (C4 (Web Text))

Max Activating Token Index: 537

Text #19

Max Range: 1.4430. Min Range: -1.4430

Max Act: 1.0168. Min Act: -0.0001

Data Index: 531323 (C4 (Web Text))

Max Activating Token Index: 519