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

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

Neuron 5885 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.4691. Min Act: -0.0000

Data Index: 642807 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.3102. Min Act: -0.0000

Data Index: 371026 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.1894. Min Act: -0.0000

Data Index: 1166362 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.1739. Min Act: -0.0000

Data Index: 471663 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.0385. Min Act: -0.0000

Data Index: 441730 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.0054. Min Act: -0.0000

Data Index: 503261 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1055926 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.0208. Min Act: -0.0000

Data Index: 248560 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9707. Min Act: -0.0000

Data Index: 12812 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.0013. Min Act: -0.0000

Data Index: 172352 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9856. Min Act: -0.0000

Data Index: 802104 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9799. Min Act: -0.0000

Data Index: 315744 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9936. Min Act: -0.0000

Data Index: 801416 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9336. Min Act: -0.0000

Data Index: 911470 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.4691. Min Range: -1.4691

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1118178 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9805. Min Act: -0.0000

Data Index: 311768 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1051609 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9115. Min Act: -0.0000

Data Index: 208701 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9104. Min Act: -0.0000

Data Index: 258783 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.4691. Min Range: -1.4691

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1263547 (C4 (Web Text))

Max Activating Token Index: 374