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

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

Neuron 3696 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.2719. Min Act: -0.0000

Data Index: 455891 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1251300 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0861. Min Act: -0.0000

Data Index: 213819 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9952. Min Act: -0.0000

Data Index: 771041 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1127404 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9206. Min Act: -0.0000

Data Index: 815602 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7950. Min Act: -0.0000

Data Index: 613933 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.8832. Min Act: -0.0000

Data Index: 882940 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7816. Min Act: -0.0000

Data Index: 1644369 (Python Code)

Max Activating Token Index: 218

Text #9

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7960. Min Act: -0.0000

Data Index: 721758 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7784. Min Act: -0.0000

Data Index: 1082942 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.8371. Min Act: -0.0000

Data Index: 115275 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7820. Min Act: -0.0000

Data Index: 251564 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7812. Min Act: 0.0000

Data Index: 1317225 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1043659 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7715. Min Act: -0.0000

Data Index: 1126819 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7654. Min Act: -0.0000

Data Index: 119738 (C4 (Web Text))

Max Activating Token Index: 178

Text #17

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7506. Min Act: -0.0000

Data Index: 856860 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7533. Min Act: -0.0000

Data Index: 152728 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.7932. Min Act: 0.0000

Data Index: 1616668 (Python Code)

Max Activating Token Index: 503