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

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

Neuron 1953 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0140. Min Range: -1.0140

Max Act: 1.0140. Min Act: -0.0001

Data Index: 697361 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.9692. Min Act: -0.0001

Data Index: 1588308 (Python Code)

Max Activating Token Index: 858

Text #2

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1399213 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.8542. Min Act: -0.0001

Data Index: 944531 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6734. Min Act: -0.0001

Data Index: 1472916 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6892. Min Act: -0.0001

Data Index: 1385249 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.7228. Min Act: -0.0001

Data Index: 1495975 (Python Code)

Max Activating Token Index: 665

Text #7

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6707. Min Act: -0.0001

Data Index: 1126287 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6647. Min Act: -0.0001

Data Index: 380196 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1569130 (Python Code)

Max Activating Token Index: 957

Text #10

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6428. Min Act: -0.0001

Data Index: 1539336 (Python Code)

Max Activating Token Index: 763

Text #11

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6826. Min Act: -0.0001

Data Index: 1454289 (Python Code)

Max Activating Token Index: 885

Text #12

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6136. Min Act: -0.0001

Data Index: 1630939 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6821. Min Act: -0.0001

Data Index: 1570482 (Python Code)

Max Activating Token Index: 611

Text #14

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6196. Min Act: -0.0001

Data Index: 1387772 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1636680 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1402404 (Python Code)

Max Activating Token Index: 953

Text #17

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.5959. Min Act: -0.0001

Data Index: 1519279 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.5943. Min Act: -0.0001

Data Index: 1376638 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 1.0140. Min Range: -1.0140

Max Act: 0.6144. Min Act: -0.0001

Data Index: 1539431 (Python Code)

Max Activating Token Index: 128