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

Dataset: The Pile

Neuron 476 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: 0.5018. Min Range: -0.5018

Max Act: 0.4936. Min Act: -0.0000

Data Index: 141319 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.5018. Min Act: -0.0000

Data Index: 608044 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1010473 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1669150 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1592716 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1633324 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4462. Min Act: -0.0000

Data Index: 407467 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4276. Min Act: -0.0000

Data Index: 917993 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4379. Min Act: -0.0000

Data Index: 925652 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4231. Min Act: -0.0000

Data Index: 243640 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3654. Min Act: -0.0000

Data Index: 1726738 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4043. Min Act: -0.0000

Data Index: 730316 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3778. Min Act: -0.0000

Data Index: 1543550 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1639170 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4171. Min Act: -0.0000

Data Index: 181705 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1989122 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3996. Min Act: -0.0000

Data Index: 235782 (The Pile)

Max Activating Token Index: 480

Text #17

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1822263 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3874. Min Act: -0.0000

Data Index: 393577 (The Pile)

Max Activating Token Index: 563

Text #19

Max Range: 0.5018. Min Range: -0.5018

Max Act: 0.3738. Min Act: -0.0000

Data Index: 542894 (The Pile)

Max Activating Token Index: 930