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

Dataset: The Pile

Neuron 3589 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: 1.8104. Min Range: -1.8104

Max Act: 1.8104. Min Act: -0.0000

Data Index: 113733 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5453. Min Act: -0.0000

Data Index: 1852674 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5368. Min Act: -0.0000

Data Index: 408536 (The Pile)

Max Activating Token Index: 804

Text #3

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6152. Min Act: -0.0000

Data Index: 1572162 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.6183. Min Act: -0.0000

Data Index: 546602 (The Pile)

Max Activating Token Index: 15

Text #5

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5240. Min Act: -0.0000

Data Index: 750520 (The Pile)

Max Activating Token Index: 330

Text #6

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4784. Min Act: -0.0000

Data Index: 896556 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4184. Min Act: -0.0000

Data Index: 1694264 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4582. Min Act: -0.0000

Data Index: 398654 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1097642 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4873. Min Act: -0.0000

Data Index: 617371 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.5203. Min Act: -0.0000

Data Index: 438918 (The Pile)

Max Activating Token Index: 317

Text #12

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1910517 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4561. Min Act: -0.0000

Data Index: 50296 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3901. Min Act: -0.0000

Data Index: 1494104 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3451. Min Act: -0.0000

Data Index: 329944 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4577. Min Act: -0.0000

Data Index: 1665186 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4110. Min Act: -0.0000

Data Index: 694280 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.3981. Min Act: -0.0000

Data Index: 752908 (The Pile)

Max Activating Token Index: 18

Text #19

Max Range: 1.8104. Min Range: -1.8104

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1276576 (The Pile)

Max Activating Token Index: 633