Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3380 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 9.8148. Min Range: -9.8148

Max Act: 9.8148. Min Act: -0.0000

Data Index: 280244 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.7276. Min Act: -0.0000

Data Index: 400091 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.7227. Min Act: -0.0000

Data Index: 1279568 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.4944. Min Act: -0.0000

Data Index: 779823 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.4638. Min Act: -0.0000

Data Index: 642592 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.1851. Min Act: -0.0000

Data Index: 69249 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 9.8148. Min Range: -9.8148

Max Act: 7.4727. Min Act: -0.0000

Data Index: 424654 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.6796. Min Act: -0.0000

Data Index: 407729 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.9501. Min Act: -0.0000

Data Index: 671743 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.7342. Min Act: -0.0000

Data Index: 70814 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.1671. Min Act: -0.0000

Data Index: 771574 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.8176. Min Act: -0.0000

Data Index: 1330321 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.4519. Min Act: -0.0000

Data Index: 688391 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.9345. Min Act: -0.0000

Data Index: 683368 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.7603. Min Act: -0.0000

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.8555. Min Act: -0.0000

Data Index: 111169 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.5345. Min Act: -0.0000

Data Index: 28948 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.7829. Min Act: -0.0000

Data Index: 201963 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.2457. Min Act: -0.0000

Data Index: 780516 (C4 (Web Text))

Max Activating Token Index: 504

Text #19

Max Range: 9.8148. Min Range: -9.8148

Max Act: 6.2290. Min Act: -0.0000

Data Index: 646942 (C4 (Web Text))

Max Activating Token Index: 92