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

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

Neuron 1768 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0318. Min Range: -2.0318

Max Act: 2.0318. Min Act: -0.0000

Data Index: 952363 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.8801. Min Act: -0.0000

Data Index: 317667 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.7179. Min Act: -0.0000

Data Index: 1214158 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.7700. Min Act: -0.0000

Data Index: 30911 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.7274. Min Act: -0.0000

Data Index: 883697 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.7197. Min Act: -0.0000

Data Index: 79642 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.7066. Min Act: -0.0000

Data Index: 1004178 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5951. Min Act: -0.0000

Data Index: 902898 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1079791 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.6556. Min Act: -0.0000

Data Index: 1055368 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.6255. Min Act: -0.0000

Data Index: 884972 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5664. Min Act: -0.0000

Data Index: 1057490 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5246. Min Act: -0.0000

Data Index: 606345 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5068. Min Act: -0.0000

Data Index: 847042 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5486. Min Act: -0.0000

Data Index: 1013158 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.3661. Min Act: -0.0000

Data Index: 1167505 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.5341. Min Act: -0.0000

Data Index: 1142664 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.3907. Min Act: -0.0000

Data Index: 902343 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.4201. Min Act: -0.0000

Data Index: 758173 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 2.0318. Min Range: -2.0318

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1143534 (C4 (Web Text))

Max Activating Token Index: 199