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

Dataset: The Pile

Neuron 790 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1675416 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.5511. Min Act: -0.0000

Data Index: 442636 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.6115. Min Act: -0.0000

Data Index: 1684242 (The Pile)

Max Activating Token Index: 265

Text #3

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.6143. Min Act: -0.0000

Data Index: 619143 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.7036. Min Act: -0.0000

Data Index: 1008876 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4884. Min Act: -0.0000

Data Index: 573509 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.5511. Min Act: -0.0000

Data Index: 1957096 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.5113. Min Act: -0.0000

Data Index: 783774 (The Pile)

Max Activating Token Index: 417

Text #8

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.5026. Min Act: -0.0000

Data Index: 804394 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4309. Min Act: -0.0000

Data Index: 191025 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1803802 (The Pile)

Max Activating Token Index: 161

Text #11

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1279025 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3915. Min Act: -0.0000

Data Index: 786251 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4879. Min Act: -0.0000

Data Index: 683994 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4527. Min Act: -0.0000

Data Index: 1015049 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3388. Min Act: -0.0000

Data Index: 1100916 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.4080. Min Act: -0.0000

Data Index: 837103 (The Pile)

Max Activating Token Index: 577

Text #17

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3976. Min Act: -0.0000

Data Index: 585432 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1302743 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 1.7036. Min Range: -1.7036

Max Act: 1.3873. Min Act: -0.0000

Data Index: 350092 (The Pile)

Max Activating Token Index: 944