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

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

Neuron 70 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.9978. Min Act: -0.0000

Data Index: 320604 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.8547. Min Act: -0.0000

Data Index: 444366 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7330. Min Act: -0.0000

Data Index: 856 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.5547. Min Act: -0.0000

Data Index: 737263 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7654. Min Act: -0.0000

Data Index: 259625 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6660. Min Act: -0.0000

Data Index: 12373 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7234. Min Act: -0.0000

Data Index: 818019 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6192. Min Act: -0.0000

Data Index: 1032372 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7118. Min Act: -0.0000

Data Index: 709445 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6858. Min Act: -0.0000

Data Index: 213925 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1077051 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6806. Min Act: -0.0000

Data Index: 624217 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7525. Min Act: -0.0000

Data Index: 246578 (C4 (Web Text))

Max Activating Token Index: 495

Text #13

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7454. Min Act: -0.0000

Data Index: 742418 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.7075. Min Act: -0.0000

Data Index: 1093073 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6094. Min Act: -0.0000

Data Index: 357429 (C4 (Web Text))

Max Activating Token Index: 342

Text #16

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6229. Min Act: -0.0000

Data Index: 680165 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.5211. Min Act: -0.0000

Data Index: 26602 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.6008. Min Act: -0.0000

Data Index: 1350425 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 1.9978. Min Range: -1.9978

Max Act: 1.5054. Min Act: -0.0000

Data Index: 475242 (C4 (Web Text))

Max Activating Token Index: 561