Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3632 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.7286. Min Act: -0.0001

Data Index: 939502 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.5997. Min Act: -0.0001

Data Index: 1242125 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.5909. Min Act: -0.0001

Data Index: 1190182 (C4 (Web Text))

Max Activating Token Index: 536

Text #3

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.5357. Min Act: -0.0001

Data Index: 949797 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.5049. Min Act: -0.0001

Data Index: 432511 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4996. Min Act: -0.0001

Data Index: 1129317 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4770. Min Act: -0.0001

Data Index: 895729 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4637. Min Act: -0.0001

Data Index: 1278593 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4423. Min Act: -0.0001

Data Index: 84885 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4854. Min Act: -0.0001

Data Index: 745771 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4741. Min Act: -0.0001

Data Index: 598921 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4651. Min Act: -0.0001

Data Index: 188064 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4483. Min Act: -0.0001

Data Index: 9639 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4725. Min Act: -0.0001

Data Index: 679265 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4852. Min Act: -0.0001

Data Index: 658922 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4243. Min Act: -0.0001

Data Index: 641327 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4489. Min Act: -0.0001

Data Index: 431595 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4442. Min Act: -0.0001

Data Index: 1178295 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4695. Min Act: -0.0001

Data Index: 20123 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.7286. Min Range: -0.7286

Max Act: 0.4281. Min Act: -0.0001

Data Index: 587994 (C4 (Web Text))

Max Activating Token Index: 217