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

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

Neuron 673 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: 1.3365. Min Range: -1.3365

Max Act: 1.3365. Min Act: -0.0001

Data Index: 414340 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2262. Min Act: -0.0001

Data Index: 1100687 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2871. Min Act: -0.0001

Data Index: 1266706 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1437. Min Act: -0.0001

Data Index: 1062708 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2200. Min Act: -0.0001

Data Index: 1181121 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1973. Min Act: -0.0001

Data Index: 609501 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0988. Min Act: -0.0001

Data Index: 943593 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1727. Min Act: -0.0001

Data Index: 300427 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1607. Min Act: -0.0001

Data Index: 735816 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1571. Min Act: -0.0001

Data Index: 383963 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1126410 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.2115. Min Act: -0.0001

Data Index: 589712 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1246. Min Act: -0.0001

Data Index: 589741 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1039631 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0921. Min Act: -0.0001

Data Index: 749416 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0849. Min Act: -0.0001

Data Index: 253692 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1066838 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1196. Min Act: -0.0001

Data Index: 1200341 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.0440. Min Act: -0.0001

Data Index: 638461 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.3365. Min Range: -1.3365

Max Act: 1.1497. Min Act: -0.0001

Data Index: 1240795 (C4 (Web Text))

Max Activating Token Index: 632