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

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

Neuron 329 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0141. Min Range: -1.0141

Max Act: 1.0141. Min Act: -0.0001

Data Index: 1018117 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.0141. Min Range: -1.0141

Max Act: 1.0067. Min Act: -0.0001

Data Index: 260841 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9338. Min Act: -0.0001

Data Index: 598594 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9556. Min Act: -0.0001

Data Index: 124314 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9014. Min Act: -0.0001

Data Index: 836696 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8595. Min Act: -0.0001

Data Index: 852889 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1257261 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8236. Min Act: -0.0001

Data Index: 849065 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8797. Min Act: -0.0001

Data Index: 196363 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8684. Min Act: -0.0001

Data Index: 1118826 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1315738 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7974. Min Act: -0.0001

Data Index: 390914 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7869. Min Act: -0.0001

Data Index: 574964 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8059. Min Act: -0.0001

Data Index: 207976 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8327. Min Act: -0.0001

Data Index: 168473 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8031. Min Act: -0.0001

Data Index: 469147 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.9048. Min Act: -0.0001

Data Index: 138396 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8186. Min Act: -0.0001

Data Index: 582100 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.8441. Min Act: -0.0001

Data Index: 1319376 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 1.0141. Min Range: -1.0141

Max Act: 0.7519. Min Act: -0.0001

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 678