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

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

Neuron 5052 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0125. Min Range: -3.0125

Max Act: 3.0125. Min Act: -0.0000

Data Index: 772204 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.0651. Min Act: -0.0000

Data Index: 247645 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.7206. Min Act: -0.0000

Data Index: 79224 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.8117. Min Act: -0.0000

Data Index: 371275 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.9123. Min Act: -0.0000

Data Index: 1224132 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.7633. Min Act: -0.0000

Data Index: 140759 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.6099. Min Act: -0.0000

Data Index: 182140 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.5831. Min Act: -0.0000

Data Index: 37377 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.5707. Min Act: -0.0000

Data Index: 627823 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.4435. Min Act: -0.0000

Data Index: 876078 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1304794 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.5216. Min Act: -0.0000

Data Index: 63961 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.4188. Min Act: -0.0000

Data Index: 430445 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.3752. Min Act: -0.0000

Data Index: 1341773 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.3524. Min Act: -0.0000

Data Index: 461383 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1113786 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.3290. Min Act: -0.0000

Data Index: 853026 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.3984. Min Act: -0.0000

Data Index: 100660 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.3970. Min Act: -0.0000

Data Index: 289316 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 3.0125. Min Range: -3.0125

Max Act: 1.4474. Min Act: -0.0000

Data Index: 113907 (C4 (Web Text))

Max Activating Token Index: 969