Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5136 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.5005. Min Act: -0.0000

Data Index: 128903 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.4085. Min Act: -0.0000

Data Index: 1005299 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3846. Min Act: -0.0000

Data Index: 1258749 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3583. Min Act: -0.0000

Data Index: 1286661 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.9027. Min Act: -0.0000

Data Index: 1277959 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.8815. Min Act: -0.0000

Data Index: 1227276 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.9999. Min Act: -0.0000

Data Index: 284241 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.8618. Min Act: -0.0000

Data Index: 304056 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.8569. Min Act: -0.0000

Data Index: 658601 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.9773. Min Act: -0.0000

Data Index: 842141 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.9359. Min Act: -0.0000

Data Index: 926171 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.9394. Min Act: -0.0000

Data Index: 724289 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.7578. Min Act: -0.0000

Data Index: 219695 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.7267. Min Act: -0.0000

Data Index: 930530 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.5879. Min Act: -0.0000

Data Index: 321495 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.3968. Min Act: -0.0000

Data Index: 1099011 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.6661. Min Act: -0.0000

Data Index: 665621 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.7832. Min Act: -0.0000

Data Index: 1218190 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.6344. Min Act: -0.0000

Data Index: 78223 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 3.5005. Min Range: -3.5005

Max Act: 2.5833. Min Act: -0.0000

Data Index: 1431296 (Python Code)

Max Activating Token Index: 139