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

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

Neuron 2691 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0900. Min Act: -0.0000

Data Index: 340269 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0834. Min Act: -0.0000

Data Index: 220332 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0453. Min Act: -0.0000

Data Index: 622322 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1601465 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0377. Min Act: -0.0000

Data Index: 548753 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1066735 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0305. Min Act: -0.0000

Data Index: 640599 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1378322 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0310. Min Act: -0.0000

Data Index: 718049 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0293. Min Act: -0.0000

Data Index: 1130599 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0310. Min Act: -0.0000

Data Index: 1427879 (Python Code)

Max Activating Token Index: 202

Text #11

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0269. Min Act: -0.0000

Data Index: 75481 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0294. Min Act: -0.0000

Data Index: 1208398 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0280. Min Act: -0.0000

Data Index: 526948 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0261. Min Act: -0.0000

Data Index: 404003 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0283. Min Act: -0.0000

Data Index: 1254391 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0275. Min Act: -0.0000

Data Index: 85332 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0268. Min Act: -0.0000

Data Index: 897321 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1196415 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0900. Min Range: -0.0900

Max Act: 0.0260. Min Act: -0.0000

Data Index: 694562 (C4 (Web Text))

Max Activating Token Index: 271