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

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

Neuron 945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.6257. Min Act: -0.0001

Data Index: 740229 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.6360. Min Act: -0.0001

Data Index: 257054 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5563. Min Act: -0.0001

Data Index: 1036918 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5763. Min Act: -0.0001

Data Index: 239400 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5554. Min Act: -0.0001

Data Index: 656914 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5276. Min Act: -0.0001

Data Index: 596878 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5430. Min Act: -0.0001

Data Index: 1244068 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5135. Min Act: -0.0001

Data Index: 488455 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4983. Min Act: -0.0001

Data Index: 1053933 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4715. Min Act: -0.0001

Data Index: 1542178 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1498694 (Python Code)

Max Activating Token Index: 814

Text #11

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4863. Min Act: -0.0001

Data Index: 249063 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4708. Min Act: -0.0001

Data Index: 559098 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4705. Min Act: -0.0001

Data Index: 362019 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4647. Min Act: -0.0001

Data Index: 720165 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1493214 (Python Code)

Max Activating Token Index: 371

Text #16

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4767. Min Act: -0.0001

Data Index: 1156059 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.5238. Min Act: -0.0001

Data Index: 912355 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4389. Min Act: -0.0001

Data Index: 514869 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.6360. Min Range: -0.6360

Max Act: 0.4223. Min Act: -0.0001

Data Index: 871456 (C4 (Web Text))

Max Activating Token Index: 657