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

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

Neuron 4881 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: 0.5353. Min Range: -0.5353

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1223617 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4682. Min Act: -0.0000

Data Index: 415758 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1324104 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1289711 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1262549 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1060725 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4195. Min Act: -0.0000

Data Index: 989095 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1179752 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1045437 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4186. Min Act: -0.0000

Data Index: 165442 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1012140 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4156. Min Act: -0.0000

Data Index: 62623 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1146816 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3968. Min Act: -0.0000

Data Index: 843720 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.4034. Min Act: -0.0000

Data Index: 260348 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3744. Min Act: -0.0000

Data Index: 856590 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3838. Min Act: -0.0000

Data Index: 186585 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3793. Min Act: -0.0000

Data Index: 811929 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3951. Min Act: -0.0000

Data Index: 169893 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.5353. Min Range: -0.5353

Max Act: 0.3787. Min Act: -0.0000

Data Index: 65325 (C4 (Web Text))

Max Activating Token Index: 943