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

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

Neuron 3616 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4135. Min Range: -4.4135

Max Act: 4.4135. Min Act: -0.0000

Data Index: 542148 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.4544. Min Act: -0.0000

Data Index: 1234225 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.5044. Min Act: -0.0000

Data Index: 448715 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.2320. Min Act: -0.0000

Data Index: 897027 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.4421. Min Act: -0.0000

Data Index: 709575 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.0445. Min Act: -0.0000

Data Index: 205742 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.5695. Min Act: -0.0000

Data Index: 1194110 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.1837. Min Act: -0.0000

Data Index: 204160 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.1012. Min Act: -0.0000

Data Index: 658908 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 4.4135. Min Range: -4.4135

Max Act: 3.0996. Min Act: -0.0000

Data Index: 854743 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.8486. Min Act: -0.0000

Data Index: 1063975 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.9325. Min Act: -0.0000

Data Index: 528920 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.6744. Min Act: -0.0000

Data Index: 663525 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.6198. Min Act: -0.0000

Data Index: 909775 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.3823. Min Act: -0.0000

Data Index: 158949 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.5982. Min Act: -0.0000

Data Index: 1305370 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.7465. Min Act: -0.0000

Data Index: 706845 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.7016. Min Act: -0.0000

Data Index: 731122 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.6690. Min Act: -0.0000

Data Index: 1176743 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 4.4135. Min Range: -4.4135

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1090982 (C4 (Web Text))

Max Activating Token Index: 827