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

Dataset: The Pile

Neuron 1675 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9344. Min Range: -3.9344

Max Act: 3.9344. Min Act: -0.0000

Data Index: 1402331 (The Pile)

Max Activating Token Index: 647

Text #1

Max Range: 3.9344. Min Range: -3.9344

Max Act: 2.1044. Min Act: -0.0000

Data Index: 1836238 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 3.9344. Min Range: -3.9344

Max Act: 1.9321. Min Act: -0.0000

Data Index: 187956 (The Pile)

Max Activating Token Index: 688

Text #3

Max Range: 3.9344. Min Range: -3.9344

Max Act: 1.6038. Min Act: -0.0000

Data Index: 990466 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 3.9344. Min Range: -3.9344

Max Act: 1.2601. Min Act: -0.0000

Data Index: 266465 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8864. Min Act: -0.0000

Data Index: 54582 (The Pile)

Max Activating Token Index: 160

Text #6

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1833018 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8765. Min Act: -0.0000

Data Index: 487623 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 3.9344. Min Range: -3.9344

Max Act: 1.0406. Min Act: -0.0000

Data Index: 571282 (The Pile)

Max Activating Token Index: 1003

Text #9

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.6856. Min Act: -0.0000

Data Index: 297887 (The Pile)

Max Activating Token Index: 570

Text #10

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1057318 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1381142 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.7739. Min Act: -0.0000

Data Index: 274728 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.9530. Min Act: -0.0000

Data Index: 1433679 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.7574. Min Act: -0.0000

Data Index: 271792 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1208681 (The Pile)

Max Activating Token Index: 516

Text #16

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1327357 (The Pile)

Max Activating Token Index: 293

Text #17

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1380021 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.8587. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 3.9344. Min Range: -3.9344

Max Act: 0.7705. Min Act: -0.0000

Data Index: 771357 (The Pile)

Max Activating Token Index: 785