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

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

Neuron 1219 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: 3.3580. Min Range: -3.3580

Max Act: 3.2362. Min Act: -0.0000

Data Index: 1431860 (Python Code)

Max Activating Token Index: 621

Text #1

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3580. Min Act: -0.0000

Data Index: 1517066 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 3.3580. Min Range: -3.3580

Max Act: 2.9933. Min Act: -0.0000

Data Index: 1584955 (Python Code)

Max Activating Token Index: 360

Text #3

Max Range: 3.3580. Min Range: -3.3580

Max Act: 3.3013. Min Act: -0.0000

Data Index: 1399404 (Python Code)

Max Activating Token Index: 54

Text #4

Max Range: 3.3580. Min Range: -3.3580

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1394471 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 3.3580. Min Range: -3.3580

Max Act: 2.4316. Min Act: -0.0000

Data Index: 1464802 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 3.3580. Min Range: -3.3580

Max Act: 2.4346. Min Act: -0.0000

Data Index: 776207 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8917. Min Act: -0.0000

Data Index: 224239 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.7407. Min Act: -0.0000

Data Index: 995066 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8248. Min Act: -0.0000

Data Index: 67318 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.9110. Min Act: -0.0000

Data Index: 669884 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8043. Min Act: -0.0000

Data Index: 377896 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8991. Min Act: -0.0000

Data Index: 1628689 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8766. Min Act: -0.0000

Data Index: 861671 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1066365 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.7379. Min Act: -0.0000

Data Index: 1318878 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1627898 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.7080. Min Act: -0.0000

Data Index: 1079731 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.8363. Min Act: -0.0000

Data Index: 846939 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 3.3580. Min Range: -3.3580

Max Act: 1.6797. Min Act: -0.0000

Data Index: 586404 (C4 (Web Text))

Max Activating Token Index: 603