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

Dataset: The Pile

Neuron 745 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: 0.8535. Min Range: -0.8535

Max Act: 0.8168. Min Act: 0.0000

Data Index: 1084296 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1615219 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1321577 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1335701 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1309550 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1425202 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5120. Min Act: -0.0000

Data Index: 1836688 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.5042. Min Act: -0.0000

Data Index: 1975652 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4765. Min Act: -0.0000

Data Index: 624956 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4792. Min Act: -0.0000

Data Index: 845828 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1814235 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4126. Min Act: -0.0000

Data Index: 993321 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4807. Min Act: -0.0000

Data Index: 248127 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4444. Min Act: -0.0000

Data Index: 774906 (The Pile)

Max Activating Token Index: 858

Text #14

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1357625 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4338. Min Act: -0.0000

Data Index: 6873 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4185. Min Act: -0.0000

Data Index: 968239 (The Pile)

Max Activating Token Index: 517

Text #17

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.4236. Min Act: -0.0000

Data Index: 204682 (The Pile)

Max Activating Token Index: 240

Text #18

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.3860. Min Act: -0.0000

Data Index: 627646 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.8535. Min Range: -0.8535

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1477386 (The Pile)

Max Activating Token Index: 946