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

Dataset: The Pile

Neuron 2822 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1916. Min Range: -3.1916

Max Act: 3.1916. Min Act: -0.0000

Data Index: 1535829 (The Pile)

Max Activating Token Index: 306

Text #1

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.8256. Min Act: -0.0000

Data Index: 993676 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 3.1916. Min Range: -3.1916

Max Act: 3.0408. Min Act: -0.0000

Data Index: 1301856 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.8224. Min Act: -0.0000

Data Index: 633869 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.1803. Min Act: -0.0000

Data Index: 185003 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.5497. Min Act: -0.0000

Data Index: 34376 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.6617. Min Act: -0.0000

Data Index: 1027755 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.6518. Min Act: -0.0000

Data Index: 326660 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.7547. Min Act: -0.0000

Data Index: 1555534 (The Pile)

Max Activating Token Index: 194

Text #9

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.7440. Min Act: -0.0000

Data Index: 935701 (The Pile)

Max Activating Token Index: 93

Text #10

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.6176. Min Act: -0.0000

Data Index: 756069 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.5906. Min Act: -0.0000

Data Index: 1402185 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.4500. Min Act: -0.0000

Data Index: 1395841 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.4298. Min Act: -0.0000

Data Index: 660559 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.4184. Min Act: -0.0000

Data Index: 971888 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.5311. Min Act: -0.0000

Data Index: 820371 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.4832. Min Act: -0.0000

Data Index: 68595 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.1992. Min Act: -0.0000

Data Index: 247069 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.3220. Min Act: -0.0000

Data Index: 1155425 (The Pile)

Max Activating Token Index: 869

Text #19

Max Range: 3.1916. Min Range: -3.1916

Max Act: 2.4376. Min Act: -0.0000

Data Index: 805137 (The Pile)

Max Activating Token Index: 379