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

Dataset: The Pile

Neuron 4731 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1488937 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1746356 (The Pile)

Max Activating Token Index: 721

Text #2

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1875145 (The Pile)

Max Activating Token Index: 704

Text #3

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1510852 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5300. Min Act: -0.0000

Data Index: 601851 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4535. Min Act: 0.0000

Data Index: 1091978 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5032. Min Act: -0.0000

Data Index: 288849 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1322073 (The Pile)

Max Activating Token Index: 793

Text #8

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1418948 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4446. Min Act: 0.0000

Data Index: 226324 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4870. Min Act: -0.0000

Data Index: 566037 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1455938 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1595656 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1841169 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4430. Min Act: -0.0000

Data Index: 1790510 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1823126 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1689392 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1396574 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4335. Min Act: 0.0000

Data Index: 917999 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4208. Min Act: -0.0000

Data Index: 986828 (The Pile)

Max Activating Token Index: 583