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

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

Neuron 2072 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: 1.0278. Min Range: -1.0278

Max Act: 1.0278. Min Act: -0.0000

Data Index: 325451 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9269. Min Act: -0.0000

Data Index: 707152 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 1.0278. Min Range: -1.0278

Max Act: 1.0084. Min Act: -0.0000

Data Index: 1021365 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9430. Min Act: -0.0000

Data Index: 141518 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9706. Min Act: -0.0000

Data Index: 469168 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.0278. Min Range: -1.0278

Max Act: 1.0098. Min Act: -0.0000

Data Index: 1291223 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9171. Min Act: -0.0000

Data Index: 611054 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.9151. Min Act: -0.0000

Data Index: 21622 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8978. Min Act: -0.0000

Data Index: 14271 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7397. Min Act: -0.0000

Data Index: 796183 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7792. Min Act: -0.0000

Data Index: 646127 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7806. Min Act: -0.0000

Data Index: 483574 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1179117 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7729. Min Act: -0.0000

Data Index: 863646 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6602. Min Act: -0.0000

Data Index: 305718 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1005592 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.7134. Min Act: -0.0000

Data Index: 23456 (C4 (Web Text))

Max Activating Token Index: 583

Text #17

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6667. Min Act: -0.0000

Data Index: 390808 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6820. Min Act: -0.0000

Data Index: 80428 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 1.0278. Min Range: -1.0278

Max Act: 0.6604. Min Act: -0.0000

Data Index: 654444 (C4 (Web Text))

Max Activating Token Index: 745