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

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

Neuron 439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1276426 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.2800. Min Act: -0.0000

Data Index: 630295 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.1715. Min Act: -0.0000

Data Index: 356037 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.1503. Min Act: -0.0000

Data Index: 100111 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.1177. Min Act: -0.0000

Data Index: 812417 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0976. Min Act: -0.0000

Data Index: 576507 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0526. Min Act: -0.0000

Data Index: 140538 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0782. Min Act: -0.0000

Data Index: 361591 (C4 (Web Text))

Max Activating Token Index: 557

Text #8

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0447. Min Act: -0.0000

Data Index: 80648 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0574. Min Act: -0.0000

Data Index: 520753 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9217. Min Act: -0.0000

Data Index: 744321 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.3797. Min Range: -1.3797

Max Act: 1.0297. Min Act: -0.0000

Data Index: 1058837 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9914. Min Act: -0.0000

Data Index: 30516 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.8942. Min Act: -0.0000

Data Index: 416284 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1323128 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1267196 (C4 (Web Text))

Max Activating Token Index: 253

Text #16

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1175976 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1019726 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.8021. Min Act: -0.0000

Data Index: 569546 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 1.3797. Min Range: -1.3797

Max Act: 0.7984. Min Act: -0.0000

Data Index: 478257 (C4 (Web Text))

Max Activating Token Index: 926