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

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

Neuron 217 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2747. Min Range: -3.2747

Max Act: 3.2747. Min Act: -0.0000

Data Index: 538524 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.8166. Min Act: -0.0000

Data Index: 407397 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.9057. Min Act: -0.0000

Data Index: 1290625 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.5703. Min Act: -0.0000

Data Index: 288417 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.4679. Min Act: -0.0000

Data Index: 390475 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.5533. Min Act: -0.0000

Data Index: 1111977 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.3964. Min Act: -0.0000

Data Index: 58688 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.2680. Min Act: -0.0000

Data Index: 357898 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.2353. Min Act: -0.0000

Data Index: 731307 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.1660. Min Act: -0.0000

Data Index: 730006 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.2799. Min Act: -0.0000

Data Index: 600340 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.0983. Min Act: -0.0000

Data Index: 330703 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.0156. Min Act: -0.0000

Data Index: 871092 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9114. Min Act: -0.0000

Data Index: 949498 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9995. Min Act: -0.0000

Data Index: 902780 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9848. Min Act: -0.0000

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 3.2747. Min Range: -3.2747

Max Act: 2.0977. Min Act: -0.0000

Data Index: 1110165 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9639. Min Act: -0.0000

Data Index: 722900 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9232. Min Act: -0.0000

Data Index: 176954 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 3.2747. Min Range: -3.2747

Max Act: 1.9243. Min Act: -0.0000

Data Index: 1084725 (C4 (Web Text))

Max Activating Token Index: 190