Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3603 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1078078 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1038141 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1262777 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4853. Min Act: -0.0001

Data Index: 374383 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4912. Min Act: -0.0001

Data Index: 97183 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1330913 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3880. Min Act: -0.0000

Data Index: 972523 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.4167. Min Act: -0.0001

Data Index: 931306 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3599. Min Act: -0.0000

Data Index: 915523 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3713. Min Act: -0.0000

Data Index: 72632 (C4 (Web Text))

Max Activating Token Index: 717

Text #10

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3423. Min Act: -0.0000

Data Index: 447147 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3351. Min Act: -0.0000

Data Index: 376287 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3568. Min Act: -0.0001

Data Index: 634532 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3068. Min Act: -0.0001

Data Index: 835461 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3286. Min Act: -0.0000

Data Index: 504012 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3216. Min Act: -0.0000

Data Index: 858323 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3205. Min Act: -0.0000

Data Index: 124517 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3164. Min Act: -0.0000

Data Index: 58579 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3175. Min Act: -0.0000

Data Index: 330224 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.7311. Min Range: -0.7311

Max Act: 0.3215. Min Act: -0.0000

Data Index: 616722 (C4 (Web Text))

Max Activating Token Index: 671