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

Dataset: The Pile

Neuron 5039 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: 1.3364. Min Range: -1.3364

Max Act: 1.1778. Min Act: -0.0000

Data Index: 953082 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.3364. Min Act: -0.0000

Data Index: 494884 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9793. Min Act: -0.0000

Data Index: 589119 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0350. Min Act: -0.0000

Data Index: 17168 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 1.3364. Min Range: -1.3364

Max Act: 1.0337. Min Act: -0.0000

Data Index: 170305 (The Pile)

Max Activating Token Index: 551

Text #5

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1576199 (The Pile)

Max Activating Token Index: 731

Text #6

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9475. Min Act: -0.0000

Data Index: 614487 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9642. Min Act: -0.0000

Data Index: 596510 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9641. Min Act: -0.0000

Data Index: 764656 (The Pile)

Max Activating Token Index: 567

Text #9

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1783900 (The Pile)

Max Activating Token Index: 647

Text #10

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9247. Min Act: -0.0000

Data Index: 685694 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9841. Min Act: -0.0000

Data Index: 62089 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8802. Min Act: -0.0000

Data Index: 147829 (The Pile)

Max Activating Token Index: 840

Text #13

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9105. Min Act: -0.0000

Data Index: 1641396 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9232. Min Act: -0.0000

Data Index: 987530 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8969. Min Act: -0.0000

Data Index: 219193 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1797943 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1120874 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9182. Min Act: -0.0000

Data Index: 442995 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 1.3364. Min Range: -1.3364

Max Act: 0.9108. Min Act: -0.0000

Data Index: 606277 (The Pile)

Max Activating Token Index: 472