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

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

Neuron 3725 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.7561. Min Act: -0.0000

Data Index: 845093 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.4196. Min Act: -0.0000

Data Index: 1651557 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.1196. Min Act: -0.0000

Data Index: 1272828 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.3116. Min Act: -0.0000

Data Index: 984981 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.1791. Min Act: -0.0000

Data Index: 545366 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.1853. Min Act: -0.0000

Data Index: 892199 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.0075. Min Act: -0.0000

Data Index: 976570 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.0303. Min Act: -0.0000

Data Index: 834897 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.1408. Min Act: -0.0000

Data Index: 692273 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.0325. Min Act: -0.0000

Data Index: 1339321 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.9472. Min Act: -0.0000

Data Index: 1002005 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.8698. Min Act: -0.0000

Data Index: 1197294 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.9613. Min Act: -0.0000

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.8602. Min Act: -0.0000

Data Index: 388125 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.9612. Min Act: -0.0000

Data Index: 305334 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 2.7561. Min Range: -2.7561

Max Act: 2.0646. Min Act: -0.0000

Data Index: 282198 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1190570 (C4 (Web Text))

Max Activating Token Index: 689

Text #17

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.9256. Min Act: -0.0000

Data Index: 1140455 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.9184. Min Act: -0.0000

Data Index: 760707 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 2.7561. Min Range: -2.7561

Max Act: 1.6835. Min Act: -0.0000

Data Index: 394721 (C4 (Web Text))

Max Activating Token Index: 186