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

Dataset: The Pile

Neuron 3135 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1713233 (The Pile)

Max Activating Token Index: 434

Text #1

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5992. Min Act: 0.0000

Data Index: 897211 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5884. Min Act: -0.0000

Data Index: 389318 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5546. Min Act: -0.0000

Data Index: 43196 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5299. Min Act: -0.0000

Data Index: 50592 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1959152 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1568310 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1401232 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1249560 (The Pile)

Max Activating Token Index: 393

Text #9

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1406291 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5081. Min Act: -0.0000

Data Index: 991543 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1048590 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5045. Min Act: -0.0000

Data Index: 229593 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5438. Min Act: -0.0000

Data Index: 902165 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5050. Min Act: -0.0000

Data Index: 549874 (The Pile)

Max Activating Token Index: 663

Text #15

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1661958 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1622364 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1101215 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4634. Min Act: -0.0000

Data Index: 828029 (The Pile)

Max Activating Token Index: 587

Text #19

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4690. Min Act: -0.0000

Data Index: 828129 (The Pile)

Max Activating Token Index: 883