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

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

Neuron 1041 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0001

Data Index: 561826 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9764. Min Act: -0.0001

Data Index: 1336357 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8430. Min Act: -0.0001

Data Index: 138621 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9466. Min Act: -0.0001

Data Index: 1258596 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8950. Min Act: -0.0001

Data Index: 27501 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8749. Min Act: -0.0001

Data Index: 410815 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8461. Min Act: -0.0001

Data Index: 1002884 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8366. Min Act: -0.0001

Data Index: 402915 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7860. Min Act: -0.0001

Data Index: 772637 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8501. Min Act: -0.0001

Data Index: 810356 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8997. Min Act: -0.0001

Data Index: 810336 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8457. Min Act: -0.0001

Data Index: 634947 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7453. Min Act: -0.0001

Data Index: 362740 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1286208 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8296. Min Act: -0.0001

Data Index: 815952 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7376. Min Act: -0.0001

Data Index: 834256 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7697. Min Act: -0.0001

Data Index: 60163 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7536. Min Act: -0.0001

Data Index: 500415 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8815. Min Act: -0.0001

Data Index: 1314522 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7714. Min Act: -0.0001

Data Index: 484493 (C4 (Web Text))

Max Activating Token Index: 95