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

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

Neuron 2458 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.6786. Min Act: -0.0000

Data Index: 1368332 (Python Code)

Max Activating Token Index: 741

Text #1

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.5493. Min Act: -0.0000

Data Index: 396365 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.5581. Min Act: -0.0000

Data Index: 178507 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.4454. Min Act: -0.0000

Data Index: 543258 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.3739. Min Act: -0.0000

Data Index: 709419 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1162608 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.3552. Min Act: -0.0000

Data Index: 1598395 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.3477. Min Act: -0.0000

Data Index: 1423441 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.3407. Min Act: -0.0000

Data Index: 912674 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.3345. Min Act: -0.0000

Data Index: 298566 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.2713. Min Act: -0.0000

Data Index: 260187 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.2101. Min Act: -0.0000

Data Index: 151301 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.2009. Min Act: -0.0000

Data Index: 712140 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1479063 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.2699. Min Act: -0.0000

Data Index: 695561 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.1491. Min Act: -0.0000

Data Index: 276792 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1536124 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.1048. Min Act: -0.0000

Data Index: 80179 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.0889. Min Act: -0.0000

Data Index: 1168363 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 1.6786. Min Range: -1.6786

Max Act: 1.0250. Min Act: -0.0000

Data Index: 421095 (C4 (Web Text))

Max Activating Token Index: 726