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

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

Neuron 2764 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.8622. Min Act: -0.0001

Data Index: 1542865 (Python Code)

Max Activating Token Index: 224

Text #1

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.7150. Min Act: -0.0001

Data Index: 1057893 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.6697. Min Act: -0.0001

Data Index: 1479626 (Python Code)

Max Activating Token Index: 816

Text #3

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.5656. Min Act: -0.0001

Data Index: 1607434 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4940. Min Act: -0.0001

Data Index: 1519859 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3336. Min Act: -0.0001

Data Index: 1381447 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4765. Min Act: -0.0001

Data Index: 1529830 (Python Code)

Max Activating Token Index: 983

Text #7

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4582. Min Act: -0.0001

Data Index: 1426546 (Python Code)

Max Activating Token Index: 90

Text #8

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4531. Min Act: -0.0001

Data Index: 1187457 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4290. Min Act: -0.0001

Data Index: 1536403 (Python Code)

Max Activating Token Index: 497

Text #10

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4348. Min Act: -0.0001

Data Index: 1558465 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4155. Min Act: -0.0001

Data Index: 1428251 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4539. Min Act: -0.0001

Data Index: 1561298 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4762. Min Act: -0.0001

Data Index: 1378464 (Python Code)

Max Activating Token Index: 71

Text #14

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4388. Min Act: -0.0001

Data Index: 1521216 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4765. Min Act: -0.0001

Data Index: 1576329 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4530. Min Act: -0.0001

Data Index: 1559634 (Python Code)

Max Activating Token Index: 602

Text #17

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.4489. Min Act: -0.0001

Data Index: 1562775 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3811. Min Act: -0.0001

Data Index: 1424696 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 1.8622. Min Range: -1.8622

Max Act: 1.3331. Min Act: -0.0001

Data Index: 1621676 (Python Code)

Max Activating Token Index: 908