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

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

Neuron 933 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.4450. Min Act: -0.0000

Data Index: 531725 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.2601. Min Act: -0.0000

Data Index: 573315 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1078075 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1062571 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0423. Min Act: -0.0000

Data Index: 314826 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1077. Min Act: -0.0000

Data Index: 776499 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.1521. Min Act: -0.0000

Data Index: 646749 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0511. Min Act: -0.0000

Data Index: 841800 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0545. Min Act: -0.0000

Data Index: 959037 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9977. Min Act: -0.0000

Data Index: 253900 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0393. Min Act: -0.0000

Data Index: 804881 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0001. Min Act: -0.0000

Data Index: 372111 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0133. Min Act: -0.0000

Data Index: 711046 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 1.4450. Min Range: -1.4450

Max Act: 1.0112. Min Act: -0.0000

Data Index: 915765 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9579. Min Act: -0.0000

Data Index: 1171074 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9632. Min Act: -0.0000

Data Index: 34538 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1090976 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1170730 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9415. Min Act: -0.0000

Data Index: 525040 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.4450. Min Range: -1.4450

Max Act: 0.9357. Min Act: -0.0000

Data Index: 958679 (C4 (Web Text))

Max Activating Token Index: 410