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

Dataset: The Pile

Neuron 4037 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3051. Min Range: -7.3051

Max Act: 7.3051. Min Act: -0.0000

Data Index: 1679535 (The Pile)

Max Activating Token Index: 269

Text #1

Max Range: 7.3051. Min Range: -7.3051

Max Act: 6.4908. Min Act: -0.0000

Data Index: 1184702 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 7.3051. Min Range: -7.3051

Max Act: 6.3803. Min Act: -0.0000

Data Index: 744326 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.8143. Min Act: -0.0000

Data Index: 1238710 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.5193. Min Act: -0.0000

Data Index: 1266886 (The Pile)

Max Activating Token Index: 326

Text #5

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.6531. Min Act: -0.0000

Data Index: 83506 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.3738. Min Act: -0.0000

Data Index: 989291 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.3723. Min Act: -0.0000

Data Index: 987352 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.8047. Min Act: -0.0000

Data Index: 1275051 (The Pile)

Max Activating Token Index: 658

Text #9

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.4686. Min Act: -0.0000

Data Index: 842258 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.9818. Min Act: -0.0000

Data Index: 652116 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.6645. Min Act: -0.0000

Data Index: 270811 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.3688. Min Act: -0.0000

Data Index: 1331618 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.4332. Min Act: -0.0000

Data Index: 1093745 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.5071. Min Act: -0.0000

Data Index: 90222 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.8935. Min Act: -0.0000

Data Index: 1156343 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 7.3051. Min Range: -7.3051

Max Act: 5.0183. Min Act: -0.0000

Data Index: 1629077 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.4842. Min Act: -0.0000

Data Index: 9109 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.7796. Min Act: -0.0000

Data Index: 398446 (The Pile)

Max Activating Token Index: 552

Text #19

Max Range: 7.3051. Min Range: -7.3051

Max Act: 4.9803. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 897