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

Dataset: The Pile

Neuron 1264 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: 1.1389. Min Range: -1.1389

Max Act: 1.1389. Min Act: -0.0000

Data Index: 568499 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.1196. Min Act: -0.0000

Data Index: 653764 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.0057. Min Act: -0.0000

Data Index: 1667521 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8643. Min Act: -0.0000

Data Index: 160674 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9817. Min Act: -0.0000

Data Index: 768315 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8077. Min Act: -0.0000

Data Index: 29371 (The Pile)

Max Activating Token Index: 52

Text #6

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1001316 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1661082 (The Pile)

Max Activating Token Index: 807

Text #8

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8560. Min Act: -0.0000

Data Index: 926567 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.1389. Min Range: -1.1389

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1267250 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1574315 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1002643 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8040. Min Act: -0.0000

Data Index: 317699 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7517. Min Act: -0.0000

Data Index: 695622 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7854. Min Act: -0.0000

Data Index: 96853 (The Pile)

Max Activating Token Index: 367

Text #15

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8334. Min Act: -0.0000

Data Index: 1432594 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8317. Min Act: -0.0000

Data Index: 382610 (The Pile)

Max Activating Token Index: 83

Text #17

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1131663 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.8189. Min Act: -0.0000

Data Index: 1730488 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 1.1389. Min Range: -1.1389

Max Act: 0.7935. Min Act: -0.0000

Data Index: 1017925 (The Pile)

Max Activating Token Index: 107