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

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

Neuron 3557 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.8290. Min Act: -0.0000

Data Index: 966489 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.7121. Min Act: -0.0000

Data Index: 420976 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2896. Min Act: -0.0000

Data Index: 93879 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1767. Min Act: -0.0000

Data Index: 1098919 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.3400. Min Act: -0.0000

Data Index: 405122 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2464. Min Act: -0.0000

Data Index: 690846 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2448. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2052. Min Act: -0.0000

Data Index: 660395 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1436. Min Act: -0.0000

Data Index: 865078 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2316. Min Act: -0.0000

Data Index: 9433 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.2372. Min Act: -0.0000

Data Index: 708927 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1246073 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.9965. Min Act: -0.0000

Data Index: 163172 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.1044. Min Act: -0.0000

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0923. Min Act: -0.0000

Data Index: 615502 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 2.8290. Min Range: -2.8290

Max Act: 1.9675. Min Act: -0.0000

Data Index: 944611 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0949. Min Act: -0.0000

Data Index: 1008548 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0998. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0471. Min Act: -0.0000

Data Index: 1007515 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 2.8290. Min Range: -2.8290

Max Act: 2.0241. Min Act: -0.0000

Data Index: 120976 (C4 (Web Text))

Max Activating Token Index: 679