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

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

Neuron 667 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: 1.0340. Min Range: -1.0340

Max Act: 1.0340. Min Act: -0.0000

Data Index: 1023543 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1210409 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.9073. Min Act: -0.0000

Data Index: 706875 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8834. Min Act: -0.0001

Data Index: 389326 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8872. Min Act: 0.0002

Data Index: 230448 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8825. Min Act: -0.0000

Data Index: 931539 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8994. Min Act: -0.0001

Data Index: 923435 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8741. Min Act: -0.0000

Data Index: 650862 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8996. Min Act: -0.0000

Data Index: 28712 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8424. Min Act: -0.0000

Data Index: 171875 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8265. Min Act: -0.0000

Data Index: 504758 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8335. Min Act: 0.0000

Data Index: 1301598 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1310565 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7695. Min Act: -0.0001

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1171740 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8031. Min Act: -0.0000

Data Index: 26600 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8257. Min Act: -0.0000

Data Index: 276855 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7963. Min Act: -0.0000

Data Index: 891666 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.8100. Min Act: -0.0000

Data Index: 6095 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.0340. Min Range: -1.0340

Max Act: 0.7578. Min Act: 0.0000

Data Index: 543980 (C4 (Web Text))

Max Activating Token Index: 609