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

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

Neuron 3864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.6740. Min Act: -0.0000

Data Index: 1507497 (Python Code)

Max Activating Token Index: 493

Text #1

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.5001. Min Act: -0.0000

Data Index: 1570728 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1982. Min Act: -0.0000

Data Index: 1562749 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2227. Min Act: -0.0000

Data Index: 1483993 (Python Code)

Max Activating Token Index: 426

Text #4

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2263. Min Act: -0.0000

Data Index: 1650506 (Python Code)

Max Activating Token Index: 415

Text #5

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2157. Min Act: -0.0000

Data Index: 1399984 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.3863. Min Act: -0.0000

Data Index: 1366883 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1464389 (Python Code)

Max Activating Token Index: 294

Text #8

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.0504. Min Act: -0.0000

Data Index: 1428341 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.3485. Min Act: -0.0000

Data Index: 1403355 (Python Code)

Max Activating Token Index: 769

Text #10

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1808. Min Act: -0.0000

Data Index: 1542459 (Python Code)

Max Activating Token Index: 948

Text #11

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.3314. Min Act: -0.0000

Data Index: 1473829 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2421. Min Act: -0.0000

Data Index: 1501837 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.0814. Min Act: -0.0000

Data Index: 1442321 (Python Code)

Max Activating Token Index: 450

Text #14

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.2296. Min Act: -0.0000

Data Index: 1430208 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1635680 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.0408. Min Act: -0.0000

Data Index: 1457923 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 3.6740. Min Range: -3.6740

Max Act: 3.1869. Min Act: -0.0000

Data Index: 1416780 (Python Code)

Max Activating Token Index: 963

Text #18

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.8003. Min Act: -0.0000

Data Index: 1612637 (Python Code)

Max Activating Token Index: 55

Text #19

Max Range: 3.6740. Min Range: -3.6740

Max Act: 2.8037. Min Act: -0.0000

Data Index: 1432351 (Python Code)

Max Activating Token Index: 173