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

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

Neuron 2909 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7809. Min Act: -0.0001

Data Index: 526296 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7667. Min Act: -0.0001

Data Index: 926656 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7520. Min Act: -0.0001

Data Index: 1390539 (Python Code)

Max Activating Token Index: 810

Text #3

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6789. Min Act: -0.0001

Data Index: 611070 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6571. Min Act: -0.0001

Data Index: 1353567 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6378. Min Act: -0.0001

Data Index: 1606079 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6898. Min Act: -0.0001

Data Index: 1111274 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6589. Min Act: -0.0001

Data Index: 261417 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1469890 (Python Code)

Max Activating Token Index: 678

Text #9

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6635. Min Act: -0.0001

Data Index: 45809 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1435382 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6621. Min Act: -0.0001

Data Index: 955749 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.5678. Min Act: -0.0001

Data Index: 289134 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6559. Min Act: -0.0001

Data Index: 1543120 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1305942 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6642. Min Act: -0.0001

Data Index: 505958 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1617854 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6439. Min Act: -0.0001

Data Index: 874010 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1430038 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.7809. Min Range: -0.7809

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1415364 (Python Code)

Max Activating Token Index: 104