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

Dataset: The Pile

Neuron 3525 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1971718 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.1050. Min Act: -0.0000

Data Index: 841985 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0302. Min Act: -0.0000

Data Index: 969912 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 1.1672. Min Range: -1.1672

Max Act: 1.0108. Min Act: -0.0000

Data Index: 944958 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1771290 (The Pile)

Max Activating Token Index: 245

Text #5

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1658912 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9625. Min Act: -0.0000

Data Index: 67088 (The Pile)

Max Activating Token Index: 542

Text #7

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9358. Min Act: -0.0000

Data Index: 1577730 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8998. Min Act: -0.0000

Data Index: 773138 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1520580 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1083609 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1658372 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9050. Min Act: 0.0000

Data Index: 1854744 (The Pile)

Max Activating Token Index: 27

Text #13

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9472. Min Act: -0.0000

Data Index: 990547 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8952. Min Act: -0.0000

Data Index: 421677 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8790. Min Act: -0.0000

Data Index: 1266754 (The Pile)

Max Activating Token Index: 961

Text #16

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.9098. Min Act: -0.0001

Data Index: 1129203 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1456046 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8564. Min Act: -0.0000

Data Index: 102040 (The Pile)

Max Activating Token Index: 952

Text #19

Max Range: 1.1672. Min Range: -1.1672

Max Act: 0.8775. Min Act: -0.0000

Data Index: 977046 (The Pile)

Max Activating Token Index: 353