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

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

Neuron 1720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1618200 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.9875. Min Act: -0.0000

Data Index: 1455595 (Python Code)

Max Activating Token Index: 325

Text #2

Max Range: 2.2865. Min Range: -2.2865

Max Act: 2.2865. Min Act: -0.0000

Data Index: 1644593 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.8769. Min Act: -0.0000

Data Index: 1530200 (Python Code)

Max Activating Token Index: 909

Text #4

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.9931. Min Act: -0.0000

Data Index: 1547056 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 2.2865. Min Range: -2.2865

Max Act: 2.0793. Min Act: -0.0000

Data Index: 1567239 (Python Code)

Max Activating Token Index: 607

Text #6

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.9251. Min Act: -0.0000

Data Index: 1488530 (Python Code)

Max Activating Token Index: 687

Text #7

Max Range: 2.2865. Min Range: -2.2865

Max Act: 2.0260. Min Act: -0.0000

Data Index: 1446710 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1380435 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 2.2865. Min Range: -2.2865

Max Act: 2.0148. Min Act: -0.0000

Data Index: 1438612 (Python Code)

Max Activating Token Index: 750

Text #10

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.8872. Min Act: -0.0000

Data Index: 1370127 (Python Code)

Max Activating Token Index: 515

Text #11

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.8741. Min Act: -0.0000

Data Index: 1461782 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7557. Min Act: -0.0000

Data Index: 1573693 (Python Code)

Max Activating Token Index: 1010

Text #13

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1471498 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7864. Min Act: -0.0000

Data Index: 1397025 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.9734. Min Act: -0.0000

Data Index: 1418278 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.8725. Min Act: -0.0000

Data Index: 1620061 (Python Code)

Max Activating Token Index: 873

Text #17

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1461901 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1364078 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 2.2865. Min Range: -2.2865

Max Act: 1.7902. Min Act: -0.0000

Data Index: 1404102 (Python Code)

Max Activating Token Index: 827