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

Dataset: The Pile

Neuron 1791 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1283575 (The Pile)

Max Activating Token Index: 476

Text #1

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7495. Min Act: -0.0000

Data Index: 549654 (The Pile)

Max Activating Token Index: 526

Text #2

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.9438. Min Act: -0.0000

Data Index: 1240630 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7125. Min Act: -0.0000

Data Index: 128375 (The Pile)

Max Activating Token Index: 142

Text #4

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7972. Min Act: -0.0000

Data Index: 1954079 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1438737 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7545. Min Act: -0.0000

Data Index: 776207 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7313. Min Act: -0.0000

Data Index: 1946631 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1902109 (The Pile)

Max Activating Token Index: 426

Text #9

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7899. Min Act: -0.0000

Data Index: 1194511 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.6655. Min Act: -0.0000

Data Index: 1921007 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.7210. Min Act: -0.0000

Data Index: 782128 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5976. Min Act: -0.0000

Data Index: 1782279 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1398485 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4758. Min Act: -0.0000

Data Index: 800528 (The Pile)

Max Activating Token Index: 680

Text #15

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4571. Min Act: -0.0000

Data Index: 138685 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1134664 (The Pile)

Max Activating Token Index: 72

Text #17

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4571. Min Act: -0.0000

Data Index: 333044 (The Pile)

Max Activating Token Index: 123

Text #18

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1919478 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 1.9438. Min Range: -1.9438

Max Act: 1.4401. Min Act: -0.0000

Data Index: 673037 (The Pile)

Max Activating Token Index: 269