Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5647 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2469. Min Act: -0.0000

Data Index: 622214 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2313. Min Act: -0.0000

Data Index: 83259 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2267. Min Act: -0.0000

Data Index: 394589 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2225. Min Act: 0.0000

Data Index: 196863 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2104. Min Act: -0.0000

Data Index: 730210 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2175. Min Act: 0.0000

Data Index: 820389 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.2138. Min Act: -0.0000

Data Index: 79233 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1058828 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1085896 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1883. Min Act: -0.0000

Data Index: 257721 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1870. Min Act: -0.0000

Data Index: 257194 (C4 (Web Text))

Max Activating Token Index: 978

Text #11

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1849. Min Act: -0.0000

Data Index: 24625 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1687. Min Act: -0.0000

Data Index: 465102 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1000042 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1740. Min Act: -0.0000

Data Index: 499413 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1305224 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1752. Min Act: -0.0000

Data Index: 408818 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1221020 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1617. Min Act: -0.0000

Data Index: 193189 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.2469. Min Range: -0.2469

Max Act: 0.1606. Min Act: -0.0000

Data Index: 515278 (C4 (Web Text))

Max Activating Token Index: 800