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

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

Neuron 4831 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: 0.7288. Min Range: -0.7288

Max Act: 0.7288. Min Act: -0.0000

Data Index: 445888 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6800. Min Act: -0.0000

Data Index: 1628976 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1437107 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1364256 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6062. Min Act: -0.0000

Data Index: 309537 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1428178 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1548986 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1338287 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5913. Min Act: -0.0000

Data Index: 223656 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1424716 (Python Code)

Max Activating Token Index: 71

Text #10

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5749. Min Act: -0.0000

Data Index: 697995 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1391753 (Python Code)

Max Activating Token Index: 525

Text #12

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1579896 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1646303 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1249728 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1450108 (Python Code)

Max Activating Token Index: 633

Text #16

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5397. Min Act: -0.0000

Data Index: 1000311 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5526. Min Act: -0.0000

Data Index: 484508 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1436481 (Python Code)

Max Activating Token Index: 43

Text #19

Max Range: 0.7288. Min Range: -0.7288

Max Act: 0.5108. Min Act: -0.0000

Data Index: 194891 (C4 (Web Text))

Max Activating Token Index: 893