Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 258 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.3445. Min Act: -0.0000

Data Index: 1577928 (Python Code)

Max Activating Token Index: 178

Text #1

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1386636 (Python Code)

Max Activating Token Index: 374

Text #2

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1413136 (Python Code)

Max Activating Token Index: 1018

Text #3

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.1072. Min Act: 0.0000

Data Index: 1499310 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1549685 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 1.3445. Min Range: -1.3445

Max Act: 1.1432. Min Act: 0.0000

Data Index: 1601090 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1540077 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9579. Min Act: 0.0000

Data Index: 1390475 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1398330 (Python Code)

Max Activating Token Index: 626

Text #9

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9781. Min Act: 0.0000

Data Index: 1394147 (Python Code)

Max Activating Token Index: 56

Text #10

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1468596 (Python Code)

Max Activating Token Index: 181

Text #11

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8387. Min Act: 0.0000

Data Index: 1468525 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1641375 (Python Code)

Max Activating Token Index: 260

Text #13

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1509101 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1465353 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1439448 (Python Code)

Max Activating Token Index: 78

Text #16

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8767. Min Act: 0.0000

Data Index: 1553065 (Python Code)

Max Activating Token Index: 886

Text #17

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.7986. Min Act: 0.0000

Data Index: 1460882 (Python Code)

Max Activating Token Index: 830

Text #18

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8371. Min Act: 0.0000

Data Index: 1655692 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 1.3445. Min Range: -1.3445

Max Act: 0.8399. Min Act: 0.0000

Data Index: 1488873 (Python Code)

Max Activating Token Index: 792