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

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

Neuron 2219 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.3842. Min Act: -0.0000

Data Index: 151556 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2009. Min Act: -0.0000

Data Index: 284219 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2555. Min Act: -0.0000

Data Index: 999819 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2424. Min Act: -0.0000

Data Index: 355017 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1996. Min Act: 0.0001

Data Index: 372739 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.1920. Min Act: -0.0000

Data Index: 31688 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2351. Min Act: -0.0000

Data Index: 639081 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.2038. Min Act: 0.0000

Data Index: 667202 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0910. Min Act: -0.0000

Data Index: 907762 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0260. Min Act: -0.0000

Data Index: 1356974 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9339. Min Act: -0.0001

Data Index: 938432 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9858. Min Act: -0.0000

Data Index: 288115 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0123. Min Act: -0.0001

Data Index: 1057206 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9236. Min Act: -0.0001

Data Index: 878489 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.3842. Min Range: -1.3842

Max Act: 1.0135. Min Act: -0.0001

Data Index: 653501 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9561. Min Act: -0.0001

Data Index: 647586 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9660. Min Act: -0.0000

Data Index: 943510 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9563. Min Act: -0.0000

Data Index: 639008 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.8913. Min Act: 0.0001

Data Index: 1329160 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 1.3842. Min Range: -1.3842

Max Act: 0.9617. Min Act: -0.0000

Data Index: 816211 (C4 (Web Text))

Max Activating Token Index: 703