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

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

Neuron 3067 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.5515. Min Act: -0.0001

Data Index: 766463 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3795. Min Act: -0.0001

Data Index: 613226 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4081. Min Act: -0.0001

Data Index: 1079662 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.4045. Min Act: -0.0001

Data Index: 361149 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3812. Min Act: -0.0001

Data Index: 194653 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1175680 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3331. Min Act: -0.0001

Data Index: 668440 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3387. Min Act: -0.0001

Data Index: 305002 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3133. Min Act: -0.0001

Data Index: 707795 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3261. Min Act: -0.0001

Data Index: 243563 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3393. Min Act: -0.0001

Data Index: 166611 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1323051 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1172274 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3132. Min Act: -0.0001

Data Index: 603687 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1105976 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3152. Min Act: -0.0001

Data Index: 986513 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3181. Min Act: -0.0001

Data Index: 1061941 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3198. Min Act: -0.0001

Data Index: 697114 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3161. Min Act: -0.0001

Data Index: 30228 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 0.5515. Min Range: -0.5515

Max Act: 0.3000. Min Act: -0.0001

Data Index: 201255 (C4 (Web Text))

Max Activating Token Index: 163