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

Dataset: The Pile

Neuron 2612 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.2993. Min Act: -0.0000

Data Index: 1199704 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9998. Min Act: -0.0000

Data Index: 5077 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0537. Min Act: -0.0000

Data Index: 605173 (The Pile)

Max Activating Token Index: 569

Text #3

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0021. Min Act: -0.0000

Data Index: 325616 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.2993. Min Range: -1.2993

Max Act: 1.0296. Min Act: -0.0000

Data Index: 283803 (The Pile)

Max Activating Token Index: 663

Text #5

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1202504 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1424277 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1893821 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9349. Min Act: -0.0000

Data Index: 900769 (The Pile)

Max Activating Token Index: 96

Text #9

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1814826 (The Pile)

Max Activating Token Index: 24

Text #10

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1644683 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9202. Min Act: -0.0000

Data Index: 194794 (The Pile)

Max Activating Token Index: 751

Text #12

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9912. Min Act: -0.0000

Data Index: 183990 (The Pile)

Max Activating Token Index: 1007

Text #13

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1862844 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1224226 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9491. Min Act: -0.0000

Data Index: 151016 (The Pile)

Max Activating Token Index: 647

Text #16

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1897942 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9543. Min Act: -0.0000

Data Index: 447565 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1236144 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.2993. Min Range: -1.2993

Max Act: 0.9731. Min Act: -0.0000

Data Index: 909840 (The Pile)

Max Activating Token Index: 978