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

Dataset: The Pile

Neuron 2892 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: 1.2510. Min Range: -1.2510

Max Act: 1.1372. Min Act: -0.0000

Data Index: 92966 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.2510. Min Act: -0.0000

Data Index: 319567 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.1296. Min Act: -0.0000

Data Index: 745154 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9621. Min Act: -0.0000

Data Index: 1059928 (The Pile)

Max Activating Token Index: 632

Text #4

Max Range: 1.2510. Min Range: -1.2510

Max Act: 1.0330. Min Act: -0.0000

Data Index: 69527 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1540001 (The Pile)

Max Activating Token Index: 673

Text #6

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.9125. Min Act: -0.0000

Data Index: 617182 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8357. Min Act: -0.0000

Data Index: 348593 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7838. Min Act: -0.0000

Data Index: 519304 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8745. Min Act: -0.0000

Data Index: 278388 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1964251 (The Pile)

Max Activating Token Index: 1000

Text #11

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7091. Min Act: -0.0000

Data Index: 1396250 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.8325. Min Act: -0.0000

Data Index: 1395653 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1978942 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7703. Min Act: -0.0000

Data Index: 10008 (The Pile)

Max Activating Token Index: 694

Text #15

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7356. Min Act: -0.0000

Data Index: 1097641 (The Pile)

Max Activating Token Index: 212

Text #16

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1996275 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.6487. Min Act: -0.0000

Data Index: 982825 (The Pile)

Max Activating Token Index: 859

Text #18

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7335. Min Act: -0.0000

Data Index: 932002 (The Pile)

Max Activating Token Index: 366

Text #19

Max Range: 1.2510. Min Range: -1.2510

Max Act: 0.7318. Min Act: -0.0000

Data Index: 174830 (The Pile)

Max Activating Token Index: 375