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

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

Neuron 2201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4258. Min Act: -0.0000

Data Index: 454800 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4288. Min Act: -0.0000

Data Index: 1043468 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4281. Min Act: -0.0000

Data Index: 90506 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4096. Min Act: -0.0000

Data Index: 993407 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4229. Min Act: -0.0000

Data Index: 248644 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4002. Min Act: -0.0000

Data Index: 206775 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4124. Min Act: -0.0000

Data Index: 147885 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4119. Min Act: -0.0000

Data Index: 995316 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4056. Min Act: -0.0000

Data Index: 249355 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3800. Min Act: -0.0000

Data Index: 132151 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4211. Min Act: -0.0000

Data Index: 358376 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3942. Min Act: -0.0000

Data Index: 800915 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4190. Min Act: -0.0000

Data Index: 988080 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4025. Min Act: -0.0000

Data Index: 577485 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3997. Min Act: -0.0000

Data Index: 1049387 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3740. Min Act: -0.0000

Data Index: 1020665 (C4 (Web Text))

Max Activating Token Index: 423

Text #16

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3893. Min Act: -0.0000

Data Index: 230968 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.4140. Min Act: -0.0000

Data Index: 685139 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3815. Min Act: -0.0000

Data Index: 113011 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.4288. Min Range: -0.4288

Max Act: 0.3843. Min Act: -0.0000

Data Index: 810676 (C4 (Web Text))

Max Activating Token Index: 520