Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.9577. Min Act: -0.0000

Data Index: 484756 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.8035. Min Act: -0.0000

Data Index: 206850 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.7042. Min Act: -0.0000

Data Index: 457532 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1207333 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.7120. Min Act: -0.0000

Data Index: 557191 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.7087. Min Act: -0.0000

Data Index: 162044 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6833. Min Act: -0.0000

Data Index: 702410 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6762. Min Act: -0.0000

Data Index: 59257 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1142546 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6660. Min Act: -0.0000

Data Index: 466715 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6520. Min Act: -0.0000

Data Index: 722107 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6196. Min Act: -0.0000

Data Index: 564061 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6499. Min Act: -0.0000

Data Index: 312345 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.5940. Min Act: -0.0000

Data Index: 138047 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6300. Min Act: -0.0000

Data Index: 454000 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6071. Min Act: -0.0000

Data Index: 281231 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6174. Min Act: -0.0000

Data Index: 518106 (C4 (Web Text))

Max Activating Token Index: 470

Text #17

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1113758 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6064. Min Act: -0.0000

Data Index: 671155 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.9577. Min Range: -0.9577

Max Act: 0.6216. Min Act: -0.0000

Data Index: 17762 (C4 (Web Text))

Max Activating Token Index: 599