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

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

Neuron 97 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: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0002

Data Index: 1562924 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8497. Min Act: -0.0002

Data Index: 1459654 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7863. Min Act: -0.0002

Data Index: 1643013 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7626. Min Act: -0.0002

Data Index: 1574404 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7496. Min Act: -0.0002

Data Index: 1605930 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7543. Min Act: -0.0002

Data Index: 1376285 (Python Code)

Max Activating Token Index: 284

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7365. Min Act: -0.0002

Data Index: 1444017 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7415. Min Act: -0.0002

Data Index: 1647348 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7267. Min Act: -0.0002

Data Index: 1360727 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7311. Min Act: -0.0002

Data Index: 1372354 (Python Code)

Max Activating Token Index: 312

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7380. Min Act: -0.0002

Data Index: 1544688 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7416. Min Act: -0.0002

Data Index: 1527041 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7173. Min Act: -0.0002

Data Index: 1537990 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7275. Min Act: -0.0002

Data Index: 1530911 (Python Code)

Max Activating Token Index: 690

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7236. Min Act: -0.0002

Data Index: 1588275 (Python Code)

Max Activating Token Index: 925

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1456922 (Python Code)

Max Activating Token Index: 468

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7147. Min Act: -0.0002

Data Index: 1633415 (Python Code)

Max Activating Token Index: 95

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7081. Min Act: -0.0002

Data Index: 1506969 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7163. Min Act: -0.0002

Data Index: 1395198 (Python Code)

Max Activating Token Index: 746

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7139. Min Act: -0.0002

Data Index: 1375228 (Python Code)

Max Activating Token Index: 631