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

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

Neuron 2036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4293. Min Range: -2.4293

Max Act: 2.4293. Min Act: -0.0000

Data Index: 1532165 (Python Code)

Max Activating Token Index: 1019

Text #1

Max Range: 2.4293. Min Range: -2.4293

Max Act: 2.0483. Min Act: -0.0000

Data Index: 1531966 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 2.4293. Min Range: -2.4293

Max Act: 2.2681. Min Act: -0.0000

Data Index: 1627094 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 2.4293. Min Range: -2.4293

Max Act: 2.0992. Min Act: -0.0000

Data Index: 1543484 (Python Code)

Max Activating Token Index: 982

Text #4

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.7993. Min Act: -0.0000

Data Index: 1534331 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.8449. Min Act: -0.0000

Data Index: 1387789 (Python Code)

Max Activating Token Index: 967

Text #6

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1540594 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.5867. Min Act: -0.0000

Data Index: 1397706 (Python Code)

Max Activating Token Index: 219

Text #8

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1420298 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1529981 (Python Code)

Max Activating Token Index: 68

Text #10

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.7302. Min Act: -0.0000

Data Index: 1519697 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.8005. Min Act: -0.0000

Data Index: 1433301 (Python Code)

Max Activating Token Index: 874

Text #12

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.5397. Min Act: -0.0000

Data Index: 1641824 (Python Code)

Max Activating Token Index: 769

Text #13

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1394884 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.5963. Min Act: -0.0000

Data Index: 1568810 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.3919. Min Act: -0.0000

Data Index: 1563729 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1606016 (Python Code)

Max Activating Token Index: 665

Text #17

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.5769. Min Act: -0.0000

Data Index: 1622057 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.3880. Min Act: -0.0000

Data Index: 1394252 (Python Code)

Max Activating Token Index: 847

Text #19

Max Range: 2.4293. Min Range: -2.4293

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1584333 (Python Code)

Max Activating Token Index: 847