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

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

Neuron 293 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.3185. Min Act: -0.0001

Data Index: 702564 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2516. Min Act: -0.0001

Data Index: 564749 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2444. Min Act: -0.0001

Data Index: 469333 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2321. Min Act: -0.0001

Data Index: 237723 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2234. Min Act: -0.0000

Data Index: 417611 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2282. Min Act: -0.0001

Data Index: 187565 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2140. Min Act: -0.0001

Data Index: 571570 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2324. Min Act: -0.0001

Data Index: 1212596 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1245277 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2012. Min Act: -0.0001

Data Index: 472445 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2020. Min Act: -0.0000

Data Index: 953149 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1240860 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2013. Min Act: -0.0001

Data Index: 697900 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1084695 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.2025. Min Act: -0.0001

Data Index: 1272115 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1860. Min Act: -0.0001

Data Index: 116980 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1825. Min Act: -0.0001

Data Index: 643267 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1826. Min Act: -0.0001

Data Index: 524537 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1163419 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 0.3185. Min Range: -0.3185

Max Act: 0.1979. Min Act: -0.0001

Data Index: 1277261 (C4 (Web Text))

Max Activating Token Index: 831