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

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

Neuron 2670 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0090. Min Act: -0.0000

Data Index: 471957 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0034. Min Act: -0.0000

Data Index: 881287 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9816. Min Act: -0.0000

Data Index: 954589 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1206596 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.0090. Min Range: -1.0090

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1153138 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9565. Min Act: -0.0000

Data Index: 953023 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9211. Min Act: -0.0000

Data Index: 670494 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9721. Min Act: -0.0000

Data Index: 678245 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9162. Min Act: -0.0000

Data Index: 93326 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8752. Min Act: -0.0000

Data Index: 545591 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9215. Min Act: -0.0000

Data Index: 804004 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9657. Min Act: -0.0000

Data Index: 761319 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9264. Min Act: -0.0000

Data Index: 992456 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.9232. Min Act: -0.0000

Data Index: 1280195 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8855. Min Act: -0.0000

Data Index: 352097 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1070951 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8747. Min Act: -0.0000

Data Index: 390010 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8988. Min Act: -0.0000

Data Index: 983766 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8349. Min Act: -0.0000

Data Index: 160433 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.0090. Min Range: -1.0090

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1014967 (C4 (Web Text))

Max Activating Token Index: 894