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

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

Neuron 5049 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9163. Min Act: -0.0000

Data Index: 570385 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9108. Min Act: -0.0000

Data Index: 630047 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9119. Min Act: -0.0000

Data Index: 549860 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9032. Min Act: -0.0000

Data Index: 668933 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1284967 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8825. Min Act: -0.0000

Data Index: 147957 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1240387 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8472. Min Act: -0.0000

Data Index: 723767 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7199. Min Act: -0.0000

Data Index: 321058 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1228901 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7118. Min Act: -0.0000

Data Index: 84434 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7163. Min Act: -0.0000

Data Index: 774421 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7390. Min Act: -0.0000

Data Index: 513565 (C4 (Web Text))

Max Activating Token Index: 379

Text #13

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6871. Min Act: -0.0000

Data Index: 581436 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7128. Min Act: -0.0000

Data Index: 459772 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6866. Min Act: -0.0000

Data Index: 647816 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6625. Min Act: -0.0000

Data Index: 242347 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6336. Min Act: -0.0000

Data Index: 829821 (C4 (Web Text))

Max Activating Token Index: 699

Text #18

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6293. Min Act: -0.0000

Data Index: 419848 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1328025 (C4 (Web Text))

Max Activating Token Index: 760