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

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

Neuron 1113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2452. Min Range: -1.2452

Max Act: 1.2452. Min Act: -0.0001

Data Index: 667667 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.9132. Min Act: -0.0001

Data Index: 326506 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7859. Min Act: -0.0001

Data Index: 1019339 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7845. Min Act: -0.0001

Data Index: 149173 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7995. Min Act: -0.0001

Data Index: 910290 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7275. Min Act: -0.0001

Data Index: 225422 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7464. Min Act: -0.0001

Data Index: 112897 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6598. Min Act: -0.0001

Data Index: 135221 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6820. Min Act: -0.0001

Data Index: 1288927 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1317939 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6510. Min Act: -0.0001

Data Index: 549222 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7125. Min Act: -0.0001

Data Index: 1142299 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7089. Min Act: -0.0001

Data Index: 416983 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7050. Min Act: -0.0001

Data Index: 390120 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6658. Min Act: -0.0001

Data Index: 776074 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7421. Min Act: -0.0001

Data Index: 1183644 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7368. Min Act: -0.0001

Data Index: 94946 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7720. Min Act: -0.0001

Data Index: 426169 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.7049. Min Act: -0.0001

Data Index: 605724 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 1.2452. Min Range: -1.2452

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1342495 (C4 (Web Text))

Max Activating Token Index: 661