Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2543 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8133. Min Act: -0.0002

Data Index: 1096284 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7102. Min Act: -0.0002

Data Index: 726684 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7127. Min Act: -0.0001

Data Index: 1346799 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5937. Min Act: -0.0001

Data Index: 963323 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6628. Min Act: -0.0001

Data Index: 965582 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6745. Min Act: -0.0001

Data Index: 4515 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6153. Min Act: -0.0001

Data Index: 80354 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6551. Min Act: -0.0002

Data Index: 1139562 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6315. Min Act: -0.0002

Data Index: 351477 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6506. Min Act: -0.0002

Data Index: 398140 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1280376 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1284437 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6211. Min Act: -0.0001

Data Index: 806569 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6802. Min Act: -0.0001

Data Index: 914340 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6507. Min Act: -0.0001

Data Index: 798933 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6157. Min Act: -0.0002

Data Index: 717730 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6253. Min Act: -0.0001

Data Index: 1127371 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6141. Min Act: -0.0002

Data Index: 212228 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6416. Min Act: -0.0002

Data Index: 1020700 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6330. Min Act: -0.0001

Data Index: 208937 (C4 (Web Text))

Max Activating Token Index: 657