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

Dataset: The Pile

Neuron 1554 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: 1.7393. Min Range: -1.7393

Max Act: 1.7393. Min Act: -0.0000

Data Index: 936759 (The Pile)

Max Activating Token Index: 169

Text #1

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5826. Min Act: 0.0000

Data Index: 1841591 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5907. Min Act: -0.0000

Data Index: 818223 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5304. Min Act: -0.0000

Data Index: 1337131 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5443. Min Act: -0.0000

Data Index: 523587 (The Pile)

Max Activating Token Index: 123

Text #5

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4037. Min Act: -0.0000

Data Index: 1854601 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4649. Min Act: -0.0000

Data Index: 623294 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1069093 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4540. Min Act: -0.0000

Data Index: 128428 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4411. Min Act: -0.0000

Data Index: 170572 (The Pile)

Max Activating Token Index: 19

Text #10

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.5175. Min Act: -0.0000

Data Index: 53056 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4291. Min Act: 0.0000

Data Index: 330784 (The Pile)

Max Activating Token Index: 1005

Text #12

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4286. Min Act: -0.0000

Data Index: 576678 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4209. Min Act: -0.0000

Data Index: 1170813 (The Pile)

Max Activating Token Index: 772

Text #14

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4055. Min Act: -0.0000

Data Index: 207722 (The Pile)

Max Activating Token Index: 524

Text #15

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.4545. Min Act: -0.0000

Data Index: 1051407 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.2969. Min Act: -0.0000

Data Index: 183514 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3621. Min Act: -0.0000

Data Index: 1749842 (The Pile)

Max Activating Token Index: 658

Text #18

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1534616 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.7393. Min Range: -1.7393

Max Act: 1.3370. Min Act: -0.0000

Data Index: 858993 (The Pile)

Max Activating Token Index: 779