Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.6001. Min Act: -0.0001

Data Index: 1625151 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.3610. Min Act: -0.0001

Data Index: 1522352 (Python Code)

Max Activating Token Index: 132

Text #2

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.4163. Min Act: -0.0000

Data Index: 748435 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.3134. Min Act: -0.0000

Data Index: 1390342 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1502738 (Python Code)

Max Activating Token Index: 326

Text #5

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2627. Min Act: -0.0000

Data Index: 680952 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2879. Min Act: -0.0001

Data Index: 1459558 (Python Code)

Max Activating Token Index: 172

Text #7

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2359. Min Act: -0.0001

Data Index: 1366550 (Python Code)

Max Activating Token Index: 223

Text #8

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1429927 (Python Code)

Max Activating Token Index: 556

Text #9

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2690. Min Act: -0.0001

Data Index: 1367463 (Python Code)

Max Activating Token Index: 164

Text #10

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2062. Min Act: -0.0001

Data Index: 1473284 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1586424 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.1591. Min Act: -0.0001

Data Index: 1409603 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1494701 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1457002 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.1623. Min Act: -0.0000

Data Index: 1656720 (Python Code)

Max Activating Token Index: 257

Text #16

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1612220 (Python Code)

Max Activating Token Index: 555

Text #17

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.0654. Min Act: -0.0001

Data Index: 1361851 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.0945. Min Act: -0.0001

Data Index: 1374879 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 1.6001. Min Range: -1.6001

Max Act: 1.0623. Min Act: -0.0001

Data Index: 1656170 (Python Code)

Max Activating Token Index: 475