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

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

Neuron 3871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0001

Data Index: 948784 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7802. Min Act: -0.0001

Data Index: 351458 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8499. Min Act: -0.0001

Data Index: 156088 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8112. Min Act: -0.0001

Data Index: 827907 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8170. Min Act: -0.0001

Data Index: 887453 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7762. Min Act: -0.0001

Data Index: 953234 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7246. Min Act: -0.0001

Data Index: 216524 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1326925 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7381. Min Act: -0.0001

Data Index: 1247172 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1288197 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7277. Min Act: -0.0001

Data Index: 1017271 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7191. Min Act: -0.0001

Data Index: 107554 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7091. Min Act: -0.0001

Data Index: 161732 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6814. Min Act: -0.0001

Data Index: 1249307 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1327329 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6745. Min Act: -0.0000

Data Index: 731655 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6942. Min Act: -0.0001

Data Index: 631992 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7165. Min Act: -0.0001

Data Index: 245436 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6709. Min Act: -0.0001

Data Index: 116198 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6852. Min Act: -0.0001

Data Index: 901865 (C4 (Web Text))

Max Activating Token Index: 20