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

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

Neuron 2687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.8063. Min Act: -0.0001

Data Index: 1113216 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.8129. Min Act: -0.0001

Data Index: 834188 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7282. Min Act: -0.0001

Data Index: 9751 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7564. Min Act: -0.0001

Data Index: 676589 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7096. Min Act: -0.0001

Data Index: 192049 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1082883 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.7211. Min Act: -0.0001

Data Index: 683835 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6928. Min Act: -0.0001

Data Index: 44830 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1160811 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6691. Min Act: -0.0001

Data Index: 603975 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6795. Min Act: -0.0001

Data Index: 37458 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6223. Min Act: -0.0001

Data Index: 300125 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6740. Min Act: -0.0001

Data Index: 672480 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6235. Min Act: -0.0001

Data Index: 812247 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6249. Min Act: -0.0001

Data Index: 203799 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6103. Min Act: -0.0001

Data Index: 1040013 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1249538 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1134484 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6471. Min Act: -0.0001

Data Index: 354029 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.8129. Min Range: -0.8129

Max Act: 0.6203. Min Act: -0.0001

Data Index: 704395 (C4 (Web Text))

Max Activating Token Index: 954