Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 510 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.4561. Min Act: -0.1700

Data Index: 1522504 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3894. Min Act: -0.1700

Data Index: 1459090 (Python Code)

Max Activating Token Index: 906

Text #2

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3836. Min Act: -0.1700

Data Index: 1440828 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3637. Min Act: -0.1700

Data Index: 1617839 (Python Code)

Max Activating Token Index: 375

Text #4

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3568. Min Act: -0.1700

Data Index: 1427725 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3629. Min Act: -0.1700

Data Index: 1417983 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.3582. Min Act: -0.1700

Data Index: 1389109 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2531. Min Act: -0.1700

Data Index: 1611680 (Python Code)

Max Activating Token Index: 765

Text #8

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2939. Min Act: -0.1700

Data Index: 1616357 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2667. Min Act: -0.1700

Data Index: 1377117 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2834. Min Act: -0.1700

Data Index: 1397075 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2542. Min Act: -0.1700

Data Index: 1442484 (Python Code)

Max Activating Token Index: 97

Text #12

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2653. Min Act: -0.1700

Data Index: 1635416 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2464. Min Act: -0.1700

Data Index: 1453614 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2068. Min Act: -0.1700

Data Index: 1584444 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2330. Min Act: -0.1700

Data Index: 1634182 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.2159. Min Act: -0.1700

Data Index: 701649 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.1707. Min Act: -0.1700

Data Index: 1454679 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.1967. Min Act: -0.1700

Data Index: 1536837 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 4.4561. Min Range: -4.4561

Max Act: 4.1829. Min Act: -0.1700

Data Index: 1548095 (Python Code)

Max Activating Token Index: 958