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

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

Neuron 2622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.3167. Min Act: -0.0000

Data Index: 697480 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1589. Min Act: -0.0000

Data Index: 67483 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.2115. Min Act: -0.0000

Data Index: 906415 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.1442. Min Act: -0.0000

Data Index: 886160 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0233. Min Act: -0.0000

Data Index: 1323463 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.3167. Min Range: -1.3167

Max Act: 1.0321. Min Act: -0.0000

Data Index: 617561 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9979. Min Act: -0.0000

Data Index: 555261 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9665. Min Act: -0.0000

Data Index: 577700 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9772. Min Act: -0.0000

Data Index: 1108591 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1278296 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1286200 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8825. Min Act: -0.0000

Data Index: 569942 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8817. Min Act: -0.0000

Data Index: 160353 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1340351 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8671. Min Act: -0.0000

Data Index: 462920 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8783. Min Act: -0.0000

Data Index: 353605 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.9050. Min Act: -0.0000

Data Index: 323145 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8741. Min Act: -0.0000

Data Index: 519438 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.8979. Min Act: -0.0000

Data Index: 1104825 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 1.3167. Min Range: -1.3167

Max Act: 0.7697. Min Act: -0.0000

Data Index: 154355 (C4 (Web Text))

Max Activating Token Index: 912