Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1051 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 4.4555. Min Range: -4.4555

Max Act: 4.4555. Min Act: -0.0000

Data Index: 1197633 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.4186. Min Act: -0.0000

Data Index: 1651306 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.0789. Min Act: -0.0000

Data Index: 117625 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9200. Min Act: -0.0000

Data Index: 1874544 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.0507. Min Act: -0.0000

Data Index: 1150333 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.2886. Min Act: -0.0000

Data Index: 1729856 (The Pile)

Max Activating Token Index: 774

Text #6

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.1309. Min Act: -0.0000

Data Index: 742053 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.8653. Min Act: -0.0000

Data Index: 86920 (The Pile)

Max Activating Token Index: 250

Text #8

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9973. Min Act: -0.0000

Data Index: 1822588 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9771. Min Act: -0.0000

Data Index: 35044 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9214. Min Act: -0.0000

Data Index: 1784776 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.8764. Min Act: -0.0000

Data Index: 1258305 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 4.4555. Min Range: -4.4555

Max Act: 3.0002. Min Act: -0.0000

Data Index: 1064632 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.8478. Min Act: -0.0000

Data Index: 418850 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9502. Min Act: -0.0000

Data Index: 1496689 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.9253. Min Act: -0.0000

Data Index: 1504433 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.3880. Min Act: -0.0000

Data Index: 353339 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.7726. Min Act: -0.0000

Data Index: 729214 (The Pile)

Max Activating Token Index: 149

Text #18

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.6299. Min Act: -0.0000

Data Index: 1053035 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 4.4555. Min Range: -4.4555

Max Act: 2.3583. Min Act: -0.0000

Data Index: 547897 (The Pile)

Max Activating Token Index: 524