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

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

Neuron 1640 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.2353. Min Act: -0.0000

Data Index: 1388899 (Python Code)

Max Activating Token Index: 197

Text #1

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1544. Min Act: -0.0000

Data Index: 1314977 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1634504 (Python Code)

Max Activating Token Index: 364

Text #3

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1641269 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0656. Min Act: -0.0000

Data Index: 1171739 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1543. Min Act: -0.0000

Data Index: 1476550 (Python Code)

Max Activating Token Index: 150

Text #6

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0041. Min Act: -0.0000

Data Index: 1355342 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9465. Min Act: -0.0000

Data Index: 909537 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1040526 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.1059. Min Act: -0.0000

Data Index: 1523545 (Python Code)

Max Activating Token Index: 432

Text #10

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1611254 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9804. Min Act: -0.0000

Data Index: 876910 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1521628 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9711. Min Act: -0.0000

Data Index: 274942 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1157689 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 1.2353. Min Range: -1.2353

Max Act: 1.0453. Min Act: -0.0000

Data Index: 1483417 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1419664 (Python Code)

Max Activating Token Index: 453

Text #17

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9187. Min Act: -0.0000

Data Index: 996190 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9758. Min Act: -0.0000

Data Index: 1650187 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 1.2353. Min Range: -1.2353

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1622038 (Python Code)

Max Activating Token Index: 997