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

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

Neuron 4501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.5225. Min Act: -0.0000

Data Index: 311938 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.3125. Min Act: -0.0000

Data Index: 984648 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2945. Min Act: -0.0001

Data Index: 746236 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2010. Min Act: -0.0001

Data Index: 591309 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2732. Min Act: -0.0000

Data Index: 1150147 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.2405. Min Act: -0.0000

Data Index: 1091782 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1823. Min Act: -0.0000

Data Index: 693682 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1251398 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.5225. Min Range: -1.5225

Max Act: 0.9840. Min Act: -0.0001

Data Index: 1281636 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1103. Min Act: -0.0000

Data Index: 98250 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.1154. Min Act: -0.0000

Data Index: 879745 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0754. Min Act: -0.0000

Data Index: 221280 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0671. Min Act: -0.0000

Data Index: 216538 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1393203 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0813. Min Act: -0.0000

Data Index: 82751 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0828. Min Act: -0.0000

Data Index: 606028 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0464. Min Act: -0.0000

Data Index: 651767 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1049579 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0446. Min Act: -0.0001

Data Index: 510829 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.5225. Min Range: -1.5225

Max Act: 1.0166. Min Act: -0.0001

Data Index: 1160310 (C4 (Web Text))

Max Activating Token Index: 925