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

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

Neuron 4312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.5512. Min Act: -0.0001

Data Index: 1404299 (Python Code)

Max Activating Token Index: 465

Text #1

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.6676. Min Act: -0.0001

Data Index: 1360525 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.5371. Min Act: -0.0001

Data Index: 1484387 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.4762. Min Act: -0.0001

Data Index: 1541388 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.4914. Min Act: -0.0001

Data Index: 1486925 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2721. Min Act: -0.0001

Data Index: 1459981 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2981. Min Act: -0.0001

Data Index: 1499353 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.3217. Min Act: -0.0001

Data Index: 1557187 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.3575. Min Act: -0.0001

Data Index: 1490275 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.3332. Min Act: -0.0001

Data Index: 1576998 (Python Code)

Max Activating Token Index: 893

Text #10

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2767. Min Act: -0.0001

Data Index: 1472780 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.3191. Min Act: -0.0001

Data Index: 1549634 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2689. Min Act: -0.0001

Data Index: 1649570 (Python Code)

Max Activating Token Index: 925

Text #13

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.3076. Min Act: -0.0001

Data Index: 1578311 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2902. Min Act: -0.0001

Data Index: 1417046 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2443. Min Act: -0.0001

Data Index: 1548848 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2112. Min Act: -0.0001

Data Index: 1499204 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2480. Min Act: -0.0001

Data Index: 1551341 (Python Code)

Max Activating Token Index: 492

Text #18

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2081. Min Act: -0.0001

Data Index: 1477890 (Python Code)

Max Activating Token Index: 273

Text #19

Max Range: 1.6676. Min Range: -1.6676

Max Act: 1.2615. Min Act: -0.0001

Data Index: 1505363 (Python Code)

Max Activating Token Index: 28