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

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

Neuron 2329 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: 0.5882. Min Range: -0.5882

Max Act: 0.5882. Min Act: -0.0000

Data Index: 932743 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.5016. Min Act: -0.0000

Data Index: 385036 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4695. Min Act: -0.0000

Data Index: 716497 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4454. Min Act: -0.0000

Data Index: 988974 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1292464 (C4 (Web Text))

Max Activating Token Index: 670

Text #5

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4163. Min Act: -0.0000

Data Index: 803828 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4450. Min Act: -0.0000

Data Index: 471919 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4477. Min Act: -0.0000

Data Index: 186097 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4179. Min Act: -0.0000

Data Index: 38448 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4001. Min Act: -0.0000

Data Index: 883313 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1157191 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.4220. Min Act: -0.0000

Data Index: 812703 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3713. Min Act: -0.0000

Data Index: 157891 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3974. Min Act: -0.0000

Data Index: 1089796 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3661. Min Act: -0.0000

Data Index: 561696 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3615. Min Act: -0.0000

Data Index: 720297 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3750. Min Act: -0.0000

Data Index: 429746 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3675. Min Act: -0.0000

Data Index: 987842 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3674. Min Act: -0.0000

Data Index: 885594 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.5882. Min Range: -0.5882

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1074533 (C4 (Web Text))

Max Activating Token Index: 623