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

Dataset: The Pile

Neuron 741 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.7105. Min Act: -0.0000

Data Index: 458079 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.4069. Min Act: -0.0000

Data Index: 1548718 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.4004. Min Act: -0.0000

Data Index: 81886 (The Pile)

Max Activating Token Index: 211

Text #3

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.2441. Min Act: -0.0000

Data Index: 68293 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.1255. Min Act: -0.0000

Data Index: 513812 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.2704. Min Act: -0.0000

Data Index: 1279428 (The Pile)

Max Activating Token Index: 736

Text #6

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.9434. Min Act: -0.0000

Data Index: 1046893 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.9382. Min Act: -0.0000

Data Index: 600914 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.0565. Min Act: -0.0000

Data Index: 957510 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.9240. Min Act: -0.0000

Data Index: 1908324 (The Pile)

Max Activating Token Index: 515

Text #10

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.0169. Min Act: -0.0000

Data Index: 1097066 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.9829. Min Act: -0.0000

Data Index: 553113 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.1163. Min Act: -0.0000

Data Index: 1585769 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.8177. Min Act: -0.0000

Data Index: 985473 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.6774. Min Act: -0.0000

Data Index: 1876551 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.0916. Min Act: -0.0000

Data Index: 640554 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 3.7105. Min Range: -3.7105

Max Act: 3.3763. Min Act: -0.0000

Data Index: 409767 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.7876. Min Act: -0.0000

Data Index: 1725334 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.8520. Min Act: -0.0000

Data Index: 1625236 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 3.7105. Min Range: -3.7105

Max Act: 2.6846. Min Act: -0.0000

Data Index: 98514 (The Pile)

Max Activating Token Index: 549