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

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

Neuron 2253 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: 0.9724. Min Range: -0.9724

Max Act: 0.9724. Min Act: -0.0001

Data Index: 63521 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8852. Min Act: -0.0001

Data Index: 917228 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9121. Min Act: -0.0001

Data Index: 10198 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9169. Min Act: -0.0001

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9235. Min Act: -0.0001

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9039. Min Act: -0.0001

Data Index: 543763 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8946. Min Act: -0.0001

Data Index: 182343 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8613. Min Act: -0.0001

Data Index: 1104993 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8196. Min Act: -0.0001

Data Index: 64219 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7888. Min Act: -0.0001

Data Index: 379519 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8417. Min Act: -0.0001

Data Index: 1602058 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8057. Min Act: -0.0001

Data Index: 1526978 (Python Code)

Max Activating Token Index: 439

Text #12

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7513. Min Act: -0.0001

Data Index: 72622 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7939. Min Act: -0.0001

Data Index: 726162 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1388665 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7106. Min Act: -0.0001

Data Index: 706490 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.8077. Min Act: -0.0001

Data Index: 538459 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6949. Min Act: -0.0001

Data Index: 263198 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7639. Min Act: -0.0001

Data Index: 1648179 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1079782 (C4 (Web Text))

Max Activating Token Index: 143