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

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

Neuron 1868 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.7148. Min Act: -0.0000

Data Index: 925432 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.6033. Min Act: -0.0000

Data Index: 373760 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.3896. Min Act: -0.0000

Data Index: 224180 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.4937. Min Act: -0.0000

Data Index: 1185120 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.2856. Min Act: -0.0000

Data Index: 693465 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 2.7148. Min Range: -2.7148

Max Act: 2.4176. Min Act: -0.0000

Data Index: 518999 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.8830. Min Act: -0.0000

Data Index: 489801 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.6694. Min Act: -0.0000

Data Index: 1638669 (Python Code)

Max Activating Token Index: 635

Text #8

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1470818 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.5423. Min Act: -0.0000

Data Index: 552548 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1516185 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.2700. Min Act: -0.0000

Data Index: 689111 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1015985 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.2571. Min Act: -0.0000

Data Index: 964445 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.3748. Min Act: -0.0000

Data Index: 1281481 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.3361. Min Act: -0.0000

Data Index: 252315 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.2689. Min Act: -0.0000

Data Index: 740960 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.3243. Min Act: -0.0000

Data Index: 857644 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.2182. Min Act: -0.0000

Data Index: 311976 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 2.7148. Min Range: -2.7148

Max Act: 1.2173. Min Act: -0.0000

Data Index: 553926 (C4 (Web Text))

Max Activating Token Index: 115