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

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

Neuron 266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.9365. Min Act: -0.0000

Data Index: 905346 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1046651 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1144336 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7626. Min Act: -0.0000

Data Index: 279737 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7945. Min Act: -0.0000

Data Index: 135477 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7564. Min Act: -0.0000

Data Index: 301055 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6960. Min Act: -0.0000

Data Index: 45867 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6685. Min Act: -0.0000

Data Index: 554769 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1197066 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1356558 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7117. Min Act: -0.0000

Data Index: 939355 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.7228. Min Act: -0.0000

Data Index: 97208 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1153563 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1216354 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6801. Min Act: -0.0000

Data Index: 363420 (C4 (Web Text))

Max Activating Token Index: 675

Text #15

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6564. Min Act: -0.0000

Data Index: 1220212 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1058936 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6499. Min Act: -0.0000

Data Index: 866502 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6900. Min Act: -0.0000

Data Index: 902266 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.9365. Min Range: -0.9365

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1332067 (C4 (Web Text))

Max Activating Token Index: 498