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

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

Neuron 2205 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: 4.3620. Min Range: -4.3620

Max Act: 4.3620. Min Act: -0.0000

Data Index: 1278100 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 4.3620. Min Range: -4.3620

Max Act: 4.0381. Min Act: -0.0000

Data Index: 1106666 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.8033. Min Act: -0.0000

Data Index: 953784 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.5575. Min Act: -0.0000

Data Index: 57150 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.5470. Min Act: -0.0000

Data Index: 1018197 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.6241. Min Act: -0.0000

Data Index: 872712 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.4400. Min Act: -0.0000

Data Index: 651240 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.3295. Min Act: -0.0000

Data Index: 180262 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.4485. Min Act: -0.0000

Data Index: 371699 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1978. Min Act: -0.0000

Data Index: 462776 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1701. Min Act: -0.0000

Data Index: 407762 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1796. Min Act: -0.0000

Data Index: 321950 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1576. Min Act: -0.0000

Data Index: 747549 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1479. Min Act: -0.0000

Data Index: 1031609 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.2860. Min Act: -0.0000

Data Index: 861866 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 4.3620. Min Range: -4.3620

Max Act: 2.9587. Min Act: -0.0000

Data Index: 685981 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 4.3620. Min Range: -4.3620

Max Act: 2.9308. Min Act: -0.0000

Data Index: 381699 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 4.3620. Min Range: -4.3620

Max Act: 3.1551. Min Act: -0.0000

Data Index: 328023 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 4.3620. Min Range: -4.3620

Max Act: 2.9915. Min Act: -0.0000

Data Index: 415339 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 4.3620. Min Range: -4.3620

Max Act: 2.9666. Min Act: -0.0000

Data Index: 609235 (C4 (Web Text))

Max Activating Token Index: 914