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

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

Neuron 3619 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: 1.0887. Min Range: -1.0887

Max Act: 1.0887. Min Act: -0.0000

Data Index: 925624 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 1.0887. Min Range: -1.0887

Max Act: 1.0593. Min Act: -0.0000

Data Index: 338868 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8930. Min Act: -0.0000

Data Index: 253207 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1181902 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7790. Min Act: -0.0000

Data Index: 79799 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1255266 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7991. Min Act: -0.0000

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1330366 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1201745 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8078. Min Act: -0.0001

Data Index: 1281880 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1212109 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8070. Min Act: -0.0000

Data Index: 511627 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1112059 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1257267 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8288. Min Act: -0.0001

Data Index: 1200673 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7479. Min Act: -0.0000

Data Index: 403028 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7906. Min Act: -0.0001

Data Index: 794617 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.8293. Min Act: -0.0000

Data Index: 50396 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7814. Min Act: -0.0001

Data Index: 1208175 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.0887. Min Range: -1.0887

Max Act: 0.7983. Min Act: -0.0000

Data Index: 566383 (C4 (Web Text))

Max Activating Token Index: 824