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

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

Neuron 922 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.5204. Min Act: -0.0000

Data Index: 146211 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4828. Min Act: -0.0000

Data Index: 297695 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4933. Min Act: -0.0000

Data Index: 275922 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4652. Min Act: -0.0000

Data Index: 518666 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4781. Min Act: -0.0000

Data Index: 781821 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1218140 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4473. Min Act: -0.0000

Data Index: 927127 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4711. Min Act: -0.0000

Data Index: 27982 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4351. Min Act: -0.0000

Data Index: 1214146 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4473. Min Act: -0.0000

Data Index: 609689 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4323. Min Act: -0.0000

Data Index: 384998 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4478. Min Act: -0.0000

Data Index: 108780 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4194. Min Act: -0.0000

Data Index: 594623 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4220. Min Act: -0.0000

Data Index: 1536253 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4237. Min Act: -0.0000

Data Index: 142110 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1033232 (C4 (Web Text))

Max Activating Token Index: 370

Text #16

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1331652 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1386130 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4261. Min Act: -0.0000

Data Index: 1111043 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.5204. Min Range: -0.5204

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1172177 (C4 (Web Text))

Max Activating Token Index: 883