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

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

Neuron 5975 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: 5.9609. Min Range: -5.9609

Max Act: 5.9609. Min Act: -0.0001

Data Index: 215817 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.3262. Min Act: -0.0001

Data Index: 451939 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.1331. Min Act: -0.0001

Data Index: 797019 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.9248. Min Act: -0.0001

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.3051. Min Act: -0.0001

Data Index: 1345154 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.0608. Min Act: -0.0001

Data Index: 901631 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.2396. Min Act: -0.0001

Data Index: 1280218 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.3179. Min Act: -0.0001

Data Index: 1031901 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.6351. Min Act: -0.0001

Data Index: 1231245 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.8463. Min Act: -0.0001

Data Index: 1185144 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.6532. Min Act: -0.0001

Data Index: 652547 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.7767. Min Act: -0.0001

Data Index: 637904 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.8374. Min Act: -0.0001

Data Index: 1305009 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.8328. Min Act: -0.0001

Data Index: 348674 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.3480. Min Act: -0.0001

Data Index: 818494 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 5.9609. Min Range: -5.9609

Max Act: 3.9975. Min Act: -0.0001

Data Index: 1337634 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.3630. Min Act: -0.0001

Data Index: 1068321 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 5.9609. Min Range: -5.9609

Max Act: 5.0648. Min Act: -0.0001

Data Index: 277853 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.6121. Min Act: -0.0001

Data Index: 862430 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 5.9609. Min Range: -5.9609

Max Act: 4.6051. Min Act: -0.0001

Data Index: 902441 (C4 (Web Text))

Max Activating Token Index: 7