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

Dataset: The Pile

Neuron 1618 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0921. Min Range: -3.0921

Max Act: 3.0921. Min Act: -0.0000

Data Index: 748061 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.5655. Min Act: -0.0000

Data Index: 589106 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.2714. Min Act: -0.0000

Data Index: 301644 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.8877. Min Act: -0.0000

Data Index: 532604 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.5144. Min Act: -0.0000

Data Index: 443693 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.2967. Min Act: -0.0000

Data Index: 1796111 (The Pile)

Max Activating Token Index: 710

Text #6

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.3915. Min Act: -0.0000

Data Index: 913314 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 3.0921. Min Range: -3.0921

Max Act: 1.7944. Min Act: -0.0000

Data Index: 271762 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.0619. Min Act: -0.0000

Data Index: 71010 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1330. Min Act: -0.0000

Data Index: 1499517 (The Pile)

Max Activating Token Index: 153

Text #10

Max Range: 3.0921. Min Range: -3.0921

Max Act: 1.6423. Min Act: -0.0000

Data Index: 1994363 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1894. Min Act: -0.0000

Data Index: 1612247 (The Pile)

Max Activating Token Index: 504

Text #12

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.6040. Min Act: -0.0000

Data Index: 1573598 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1901209 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1002. Min Act: -0.0000

Data Index: 1979950 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 3.0921. Min Range: -3.0921

Max Act: 1.8065. Min Act: -0.0000

Data Index: 1993764 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1749280 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1989259 (The Pile)

Max Activating Token Index: 648

Text #18

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.4145. Min Act: -0.0000

Data Index: 1134470 (The Pile)

Max Activating Token Index: 813

Text #19

Max Range: 3.0921. Min Range: -3.0921

Max Act: 2.1382. Min Act: -0.0000

Data Index: 663289 (The Pile)

Max Activating Token Index: 195