Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6423. Min Range: -4.6423

Max Act: 4.4570. Min Act: -0.0001

Data Index: 356165 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 4.6423. Min Range: -4.6423

Max Act: 4.6423. Min Act: -0.0000

Data Index: 172225 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8365. Min Act: -0.0000

Data Index: 1332478 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8592. Min Act: -0.0000

Data Index: 1352055 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8689. Min Act: -0.0001

Data Index: 1094248 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 4.6423. Min Range: -4.6423

Max Act: 4.2264. Min Act: -0.0000

Data Index: 486564 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8914. Min Act: -0.0001

Data Index: 1168186 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 4.6423. Min Range: -4.6423

Max Act: 4.0461. Min Act: -0.0000

Data Index: 814157 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8037. Min Act: -0.0000

Data Index: 521950 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8402. Min Act: -0.0001

Data Index: 1318815 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.8426. Min Act: -0.0000

Data Index: 1351083 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.9565. Min Act: -0.0001

Data Index: 1245647 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.7811. Min Act: -0.0000

Data Index: 264837 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.5946. Min Act: -0.0000

Data Index: 71483 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.5877. Min Act: -0.0000

Data Index: 1108518 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.7165. Min Act: -0.0000

Data Index: 628756 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.2694. Min Act: -0.0001

Data Index: 145189 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 4.6423. Min Range: -4.6423

Max Act: 4.2271. Min Act: -0.0001

Data Index: 1289217 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.5370. Min Act: -0.0000

Data Index: 717084 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 4.6423. Min Range: -4.6423

Max Act: 3.5422. Min Act: -0.0001

Data Index: 888473 (C4 (Web Text))

Max Activating Token Index: 980