Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4891 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.2952. Min Range: -3.2952

Max Act: 3.2952. Min Act: -0.0000

Data Index: 337989 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.8373. Min Act: -0.0000

Data Index: 900179 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.5475. Min Act: -0.0000

Data Index: 1295445 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.5121. Min Act: -0.0000

Data Index: 186393 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.4508. Min Act: -0.0000

Data Index: 838405 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1089374 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.5005. Min Act: -0.0000

Data Index: 785860 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.4467. Min Act: -0.0000

Data Index: 22573 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.5563. Min Act: -0.0000

Data Index: 249136 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.3853. Min Act: -0.0000

Data Index: 138668 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.4199. Min Act: -0.0000

Data Index: 679955 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.3457. Min Act: -0.0000

Data Index: 888333 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.4825. Min Act: -0.0000

Data Index: 1217194 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.3954. Min Act: -0.0000

Data Index: 776634 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.2575. Min Act: -0.0000

Data Index: 569385 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.3305. Min Act: -0.0000

Data Index: 702963 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.4409. Min Act: -0.0000

Data Index: 683579 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.1820. Min Act: -0.0000

Data Index: 370701 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.2880. Min Act: -0.0000

Data Index: 1079694 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 3.2952. Min Range: -3.2952

Max Act: 2.2705. Min Act: -0.0000

Data Index: 1297231 (C4 (Web Text))

Max Activating Token Index: 548