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

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

Neuron 113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.5085. Min Act: -0.0001

Data Index: 226119 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2716. Min Act: -0.0001

Data Index: 738907 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2210. Min Act: -0.0001

Data Index: 806141 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.1752. Min Act: -0.0001

Data Index: 931096 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2131. Min Act: -0.0001

Data Index: 1151104 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2780. Min Act: -0.0001

Data Index: 999547 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2353. Min Act: -0.0001

Data Index: 321543 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.2129. Min Act: -0.0001

Data Index: 888369 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.1391. Min Act: -0.0001

Data Index: 652790 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.1074. Min Act: -0.0001

Data Index: 32962 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0787. Min Act: -0.0001

Data Index: 817588 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.1421. Min Act: -0.0001

Data Index: 178490 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0407. Min Act: -0.0001

Data Index: 1201785 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.1501. Min Act: -0.0001

Data Index: 51976 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0035. Min Act: -0.0001

Data Index: 305363 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0899. Min Act: -0.0001

Data Index: 443905 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0461. Min Act: -0.0001

Data Index: 215916 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0103. Min Act: -0.0001

Data Index: 376672 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.5085. Min Range: -1.5085

Max Act: 1.0752. Min Act: -0.0001

Data Index: 507620 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.5085. Min Range: -1.5085

Max Act: 0.9688. Min Act: -0.0001

Data Index: 170157 (C4 (Web Text))

Max Activating Token Index: 680