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

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

Neuron 474 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: 5.7229. Min Range: -5.7229

Max Act: 5.7229. Min Act: -0.1700

Data Index: 1656232 (Python Code)

Max Activating Token Index: 877

Text #1

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.5894. Min Act: -0.1700

Data Index: 1397140 (Python Code)

Max Activating Token Index: 281

Text #2

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.3603. Min Act: -0.1700

Data Index: 1464291 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.3844. Min Act: -0.1700

Data Index: 1491323 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.2594. Min Act: -0.1700

Data Index: 1408201 (Python Code)

Max Activating Token Index: 615

Text #5

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.2690. Min Act: -0.1700

Data Index: 1485822 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.2565. Min Act: -0.1700

Data Index: 1398142 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.2549. Min Act: -0.1700

Data Index: 1368919 (Python Code)

Max Activating Token Index: 700

Text #8

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.1651. Min Act: -0.1700

Data Index: 1420783 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.1636. Min Act: -0.1700

Data Index: 1449266 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.1563. Min Act: -0.1700

Data Index: 1486217 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.1205. Min Act: -0.1700

Data Index: 1466851 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.1126. Min Act: -0.1700

Data Index: 1634407 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0954. Min Act: -0.1700

Data Index: 1539505 (Python Code)

Max Activating Token Index: 159

Text #14

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0960. Min Act: -0.1700

Data Index: 1653940 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0415. Min Act: -0.1700

Data Index: 1417174 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0610. Min Act: -0.1700

Data Index: 1432169 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0462. Min Act: -0.1700

Data Index: 1499177 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0582. Min Act: -0.1700

Data Index: 1643835 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 5.7229. Min Range: -5.7229

Max Act: 5.0333. Min Act: -0.1700

Data Index: 1638567 (Python Code)

Max Activating Token Index: 538