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

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

Neuron 4752 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1202512 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5089. Min Act: -0.0000

Data Index: 191282 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1313580 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5120. Min Act: -0.0000

Data Index: 581281 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5121. Min Act: -0.0000

Data Index: 921055 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1008809 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4442. Min Act: -0.0000

Data Index: 489732 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1078550 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1154848 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5031. Min Act: -0.0000

Data Index: 565389 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5369. Min Act: -0.0000

Data Index: 188508 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4214. Min Act: -0.0000

Data Index: 584335 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4593. Min Act: -0.0000

Data Index: 654091 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1107149 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4811. Min Act: -0.0000

Data Index: 194919 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4931. Min Act: -0.0000

Data Index: 305521 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4281. Min Act: -0.0000

Data Index: 994810 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4885. Min Act: -0.0000

Data Index: 317184 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4392. Min Act: -0.0000

Data Index: 221562 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.5369. Min Range: -0.5369

Max Act: 0.4868. Min Act: -0.0000

Data Index: 392668 (C4 (Web Text))

Max Activating Token Index: 398