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

Dataset: The Pile

Neuron 1151 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: 3.7304. Min Range: -3.7304

Max Act: 3.7304. Min Act: -0.0000

Data Index: 1420027 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3987. Min Act: -0.0000

Data Index: 1131216 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.5427. Min Act: -0.0000

Data Index: 43467 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3406. Min Act: -0.0000

Data Index: 804169 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.4525. Min Act: -0.0000

Data Index: 764187 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.4143. Min Act: -0.0000

Data Index: 345495 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3734. Min Act: -0.0000

Data Index: 1454701 (The Pile)

Max Activating Token Index: 304

Text #7

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3764. Min Act: -0.0000

Data Index: 604466 (The Pile)

Max Activating Token Index: 586

Text #8

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3796. Min Act: -0.0000

Data Index: 1646864 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3583. Min Act: -0.0000

Data Index: 843126 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.3342. Min Act: -0.0000

Data Index: 1633477 (The Pile)

Max Activating Token Index: 479

Text #11

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.4422. Min Act: -0.0000

Data Index: 453999 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.4464. Min Act: -0.0000

Data Index: 1373291 (The Pile)

Max Activating Token Index: 173

Text #13

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.2538. Min Act: -0.0000

Data Index: 1921867 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.2028. Min Act: -0.0000

Data Index: 1599210 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 3.7304. Min Range: -3.7304

Max Act: 2.9845. Min Act: -0.0000

Data Index: 1594536 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.0989. Min Act: -0.0000

Data Index: 1962912 (The Pile)

Max Activating Token Index: 267

Text #17

Max Range: 3.7304. Min Range: -3.7304

Max Act: 3.1025. Min Act: -0.0000

Data Index: 728013 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 3.7304. Min Range: -3.7304

Max Act: 2.8904. Min Act: -0.0000

Data Index: 1019051 (The Pile)

Max Activating Token Index: 535

Text #19

Max Range: 3.7304. Min Range: -3.7304

Max Act: 2.9203. Min Act: -0.0000

Data Index: 260789 (The Pile)

Max Activating Token Index: 563