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

Dataset: The Pile

Neuron 221 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1806872 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5958. Min Act: -0.0000

Data Index: 123125 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1389159 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4674. Min Act: -0.0000

Data Index: 669925 (The Pile)

Max Activating Token Index: 956

Text #4

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4546. Min Act: -0.0000

Data Index: 69853 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4487. Min Act: -0.0000

Data Index: 185678 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1741994 (The Pile)

Max Activating Token Index: 679

Text #7

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4184. Min Act: -0.0000

Data Index: 221058 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1499109 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3880. Min Act: -0.0000

Data Index: 320860 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3872. Min Act: -0.0000

Data Index: 767804 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3946. Min Act: -0.0000

Data Index: 821514 (The Pile)

Max Activating Token Index: 140

Text #12

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1937321 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3878. Min Act: -0.0000

Data Index: 941346 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1626843 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1364765 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3643. Min Act: -0.0000

Data Index: 267353 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3483. Min Act: -0.0000

Data Index: 813359 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.4089. Min Act: -0.0000

Data Index: 1536678 (The Pile)

Max Activating Token Index: 862

Text #19

Max Range: 0.6440. Min Range: -0.6440

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1578208 (The Pile)

Max Activating Token Index: 572