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

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

Neuron 3990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1319. Min Range: -1.1319

Max Act: 1.1319. Min Act: -0.0001

Data Index: 1128831 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 1.1319. Min Range: -1.1319

Max Act: 1.0889. Min Act: -0.0001

Data Index: 1306931 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 1.1319. Min Range: -1.1319

Max Act: 1.0299. Min Act: -0.0001

Data Index: 191521 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.1319. Min Range: -1.1319

Max Act: 1.0310. Min Act: -0.0001

Data Index: 1180129 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.9412. Min Act: -0.0001

Data Index: 164969 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8729. Min Act: -0.0001

Data Index: 635237 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8686. Min Act: -0.0001

Data Index: 392116 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8618. Min Act: -0.0001

Data Index: 902482 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8786. Min Act: -0.0001

Data Index: 1221514 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7850. Min Act: -0.0001

Data Index: 462037 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8547. Min Act: -0.0001

Data Index: 1016376 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8231. Min Act: -0.0001

Data Index: 222442 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.8041. Min Act: -0.0001

Data Index: 855724 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7507. Min Act: -0.0001

Data Index: 1101818 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7728. Min Act: -0.0001

Data Index: 1029251 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7400. Min Act: -0.0001

Data Index: 867066 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1045899 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7241. Min Act: -0.0001

Data Index: 336345 (C4 (Web Text))

Max Activating Token Index: 743

Text #18

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7670. Min Act: -0.0001

Data Index: 734088 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 1.1319. Min Range: -1.1319

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1068663 (C4 (Web Text))

Max Activating Token Index: 925