Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 811 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1491522 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6255. Min Act: -0.0000

Data Index: 440662 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1355804 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1902458 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5599. Min Act: -0.0000

Data Index: 463187 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1623492 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4884. Min Act: -0.0000

Data Index: 889140 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5348. Min Act: -0.0000

Data Index: 668728 (The Pile)

Max Activating Token Index: 820

Text #8

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4933. Min Act: -0.0000

Data Index: 840092 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1710004 (The Pile)

Max Activating Token Index: 586

Text #10

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1277714 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1697164 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4641. Min Act: -0.0000

Data Index: 464992 (The Pile)

Max Activating Token Index: 837

Text #13

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4614. Min Act: -0.0000

Data Index: 323178 (The Pile)

Max Activating Token Index: 216

Text #14

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4758. Min Act: -0.0000

Data Index: 865980 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1209667 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1755237 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4283. Min Act: -0.0000

Data Index: 798684 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4409. Min Act: -0.0000

Data Index: 997656 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1423421 (The Pile)

Max Activating Token Index: 198