Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.3429. Min Act: -0.0000

Data Index: 543440 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.1222. Min Act: -0.0000

Data Index: 1294037 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1109727 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.1537. Min Act: -0.0001

Data Index: 747121 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0372. Min Act: -0.0001

Data Index: 914846 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.1459. Min Act: -0.0000

Data Index: 778681 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0886. Min Act: -0.0001

Data Index: 1161058 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.1425. Min Act: -0.0001

Data Index: 735872 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0471. Min Act: -0.0000

Data Index: 688068 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0435. Min Act: -0.0001

Data Index: 683706 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.9532. Min Act: -0.0000

Data Index: 319078 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.9973. Min Act: -0.0001

Data Index: 503359 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0049. Min Act: -0.0000

Data Index: 1182204 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1266061 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 2.3429. Min Range: -2.3429

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1100002 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.8899. Min Act: -0.0000

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.9527. Min Act: -0.0001

Data Index: 54379 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.9287. Min Act: -0.0000

Data Index: 651723 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.8565. Min Act: -0.0000

Data Index: 762254 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 2.3429. Min Range: -2.3429

Max Act: 1.8522. Min Act: -0.0001

Data Index: 732759 (C4 (Web Text))

Max Activating Token Index: 771