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

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

Neuron 2141 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.5961. Min Act: -0.0002

Data Index: 1177054 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3612. Min Act: -0.0002

Data Index: 427648 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.2532. Min Act: -0.0002

Data Index: 1133844 (C4 (Web Text))

Max Activating Token Index: 113

Text #3

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3878. Min Act: -0.0002

Data Index: 221097 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4217. Min Act: -0.0002

Data Index: 119227 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4318. Min Act: -0.0002

Data Index: 339025 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.1717. Min Act: -0.0002

Data Index: 291373 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4146. Min Act: -0.0002

Data Index: 5254 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4214. Min Act: -0.0002

Data Index: 984275 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4298. Min Act: -0.0002

Data Index: 911532 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3948. Min Act: -0.0002

Data Index: 29745 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3347. Min Act: -0.0002

Data Index: 738799 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4556. Min Act: -0.0002

Data Index: 965383 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.2737. Min Act: -0.0002

Data Index: 879363 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3073. Min Act: -0.0002

Data Index: 694439 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3150. Min Act: -0.0002

Data Index: 83701 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.1256. Min Act: -0.0002

Data Index: 839011 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.4112. Min Act: -0.0002

Data Index: 959038 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.3661. Min Act: -0.0002

Data Index: 556290 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 1.5961. Min Range: -1.5961

Max Act: 1.1716. Min Act: -0.0002

Data Index: 901863 (C4 (Web Text))

Max Activating Token Index: 51