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

Dataset: The Pile

Neuron 1546 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: 0.4638. Min Range: -0.4638

Max Act: 0.4638. Min Act: -0.0000

Data Index: 568709 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.4271. Min Act: -0.0000

Data Index: 821506 (The Pile)

Max Activating Token Index: 714

Text #2

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1646836 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1622137 (The Pile)

Max Activating Token Index: 456

Text #4

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3802. Min Act: -0.0000

Data Index: 485683 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1944923 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3397. Min Act: -0.0000

Data Index: 82961 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3643. Min Act: -0.0000

Data Index: 1840804 (The Pile)

Max Activating Token Index: 616

Text #8

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1855677 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3508. Min Act: -0.0000

Data Index: 250265 (The Pile)

Max Activating Token Index: 343

Text #10

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1382705 (The Pile)

Max Activating Token Index: 184

Text #11

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3680. Min Act: -0.0000

Data Index: 739372 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3301. Min Act: -0.0000

Data Index: 1209065 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3245. Min Act: -0.0000

Data Index: 1386066 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1086267 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1468890 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1656336 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3060. Min Act: -0.0000

Data Index: 339298 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3209. Min Act: -0.0000

Data Index: 149062 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 0.4638. Min Range: -0.4638

Max Act: 0.3201. Min Act: -0.0000

Data Index: 469468 (The Pile)

Max Activating Token Index: 101