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

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

Neuron 1225 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1395215 (Python Code)

Max Activating Token Index: 121

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1554088 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1646191 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1417110 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1493019 (Python Code)

Max Activating Token Index: 827

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0436. Min Act: -0.0002

Data Index: 1602900 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1655823 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1541208 (Python Code)

Max Activating Token Index: 403

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1395646 (Python Code)

Max Activating Token Index: 242

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1602381 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1446054 (Python Code)

Max Activating Token Index: 199

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1465010 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1622983 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1457417 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1651170 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1496988 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1473872 (Python Code)

Max Activating Token Index: 883

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1562477 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0416. Min Act: -0.0002

Data Index: 1608112 (Python Code)

Max Activating Token Index: 835

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1587218 (Python Code)

Max Activating Token Index: 605