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

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

Neuron 1668 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: 2.0737. Min Range: -2.0737

Max Act: 2.0737. Min Act: -0.0000

Data Index: 1424501 (Python Code)

Max Activating Token Index: 947

Text #1

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.8069. Min Act: -0.0000

Data Index: 1055617 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.7515. Min Act: -0.0000

Data Index: 374240 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.6601. Min Act: -0.0001

Data Index: 1356559 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.6164. Min Act: -0.0000

Data Index: 761340 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.6909. Min Act: -0.0000

Data Index: 351592 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.8855. Min Act: -0.0000

Data Index: 1398616 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.6608. Min Act: -0.0000

Data Index: 610365 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5262. Min Act: -0.0001

Data Index: 614714 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5897. Min Act: -0.0000

Data Index: 1207919 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5144. Min Act: -0.0000

Data Index: 214782 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.6852. Min Act: -0.0000

Data Index: 1372226 (Python Code)

Max Activating Token Index: 519

Text #12

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.4881. Min Act: -0.0000

Data Index: 1056719 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1339036 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5289. Min Act: -0.0000

Data Index: 1177381 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1288398 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.4226. Min Act: -0.0001

Data Index: 454996 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5249. Min Act: -0.0000

Data Index: 26936 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.4691. Min Act: -0.0000

Data Index: 543460 (C4 (Web Text))

Max Activating Token Index: 106

Text #19

Max Range: 2.0737. Min Range: -2.0737

Max Act: 1.5553. Min Act: -0.0000

Data Index: 1053594 (C4 (Web Text))

Max Activating Token Index: 49