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

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

Neuron 5486 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.8481. Min Act: -0.0000

Data Index: 12168 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.9365. Min Act: -0.0000

Data Index: 1310377 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6802. Min Act: -0.0000

Data Index: 559738 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.7636. Min Act: -0.0000

Data Index: 647186 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6184. Min Act: -0.0000

Data Index: 165880 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.9064. Min Act: -0.0000

Data Index: 738663 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6027. Min Act: -0.0000

Data Index: 814794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6786. Min Act: -0.0000

Data Index: 1013003 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.7356. Min Act: -0.0000

Data Index: 493007 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.5045. Min Act: -0.0000

Data Index: 112480 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6202. Min Act: -0.0000

Data Index: 276776 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.5682. Min Act: -0.0000

Data Index: 745107 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.5389. Min Act: -0.0000

Data Index: 402037 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.4542. Min Act: -0.0000

Data Index: 794523 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6107. Min Act: -0.0000

Data Index: 286823 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6170. Min Act: -0.0000

Data Index: 411783 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.5135. Min Act: -0.0000

Data Index: 816198 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.6052. Min Act: -0.0000

Data Index: 944029 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.5648. Min Act: -0.0000

Data Index: 380326 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 1.9365. Min Range: -1.9365

Max Act: 1.4290. Min Act: -0.0000

Data Index: 823193 (C4 (Web Text))

Max Activating Token Index: 136