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

Dataset: The Pile

Neuron 3765 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1631672 (The Pile)

Max Activating Token Index: 943

Text #1

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1071276 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6210. Min Act: -0.0000

Data Index: 582506 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6253. Min Act: -0.0000

Data Index: 623444 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1994853 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1071487 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6057. Min Act: -0.0000

Data Index: 65156 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1237124 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6094. Min Act: 0.0000

Data Index: 732170 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1212673 (The Pile)

Max Activating Token Index: 608

Text #10

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5289. Min Act: -0.0000

Data Index: 786106 (The Pile)

Max Activating Token Index: 951

Text #11

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1918670 (The Pile)

Max Activating Token Index: 38

Text #12

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5561. Min Act: -0.0000

Data Index: 406207 (The Pile)

Max Activating Token Index: 563

Text #13

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5443. Min Act: -0.0000

Data Index: 260115 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5381. Min Act: -0.0000

Data Index: 327669 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5597. Min Act: -0.0000

Data Index: 201377 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5440. Min Act: -0.0000

Data Index: 803806 (The Pile)

Max Activating Token Index: 457

Text #17

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5280. Min Act: -0.0000

Data Index: 585874 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1520759 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1895707 (The Pile)

Max Activating Token Index: 279