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

Dataset: The Pile

Neuron 8 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4752. Min Range: -1.4752

Max Act: 1.4752. Min Act: -0.0000

Data Index: 415415 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.4752. Min Range: -1.4752

Max Act: 1.2030. Min Act: -0.0000

Data Index: 431067 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 1.4752. Min Range: -1.4752

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1378053 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 1.4752. Min Range: -1.4752

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1346346 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8978. Min Act: -0.0000

Data Index: 183662 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8651. Min Act: -0.0000

Data Index: 361985 (The Pile)

Max Activating Token Index: 635

Text #6

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8579. Min Act: -0.0000

Data Index: 1984056 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1445510 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1106915 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8180. Min Act: -0.0000

Data Index: 10065 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8207. Min Act: -0.0000

Data Index: 783752 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8705. Min Act: -0.0000

Data Index: 295163 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1934455 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1694605 (The Pile)

Max Activating Token Index: 401

Text #14

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1102522 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1284140 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7113. Min Act: -0.0000

Data Index: 520393 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8074. Min Act: -0.0000

Data Index: 680670 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1653685 (The Pile)

Max Activating Token Index: 122

Text #19

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6867. Min Act: -0.0000

Data Index: 844176 (The Pile)

Max Activating Token Index: 773