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

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

Neuron 2992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.6421. Min Act: -0.0001

Data Index: 14199 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.4945. Min Act: -0.0001

Data Index: 575176 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.4325. Min Act: -0.0001

Data Index: 1072967 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.4060. Min Act: -0.0001

Data Index: 389851 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.4095. Min Act: -0.0001

Data Index: 875075 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.3339. Min Act: -0.0001

Data Index: 869360 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2845. Min Act: -0.0001

Data Index: 733975 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.3019. Min Act: -0.0001

Data Index: 621878 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.3179. Min Act: -0.0001

Data Index: 891328 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.3131. Min Act: -0.0001

Data Index: 878189 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2760. Min Act: -0.0001

Data Index: 821591 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2711. Min Act: -0.0001

Data Index: 865781 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2890. Min Act: -0.0001

Data Index: 345384 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2876. Min Act: -0.0001

Data Index: 410779 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2572. Min Act: -0.0001

Data Index: 798456 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2627. Min Act: -0.0001

Data Index: 293884 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2595. Min Act: -0.0001

Data Index: 721782 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2645. Min Act: -0.0001

Data Index: 133126 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2688. Min Act: -0.0001

Data Index: 487387 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.6421. Min Range: -0.6421

Max Act: 0.2584. Min Act: -0.0001

Data Index: 512909 (C4 (Web Text))

Max Activating Token Index: 15