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

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

Neuron 594 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: 3.6123. Min Range: -3.6123

Max Act: 3.6123. Min Act: -0.1700

Data Index: 1444166 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5909. Min Act: -0.1700

Data Index: 1643487 (Python Code)

Max Activating Token Index: 757

Text #2

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5964. Min Act: -0.1700

Data Index: 1405749 (Python Code)

Max Activating Token Index: 554

Text #3

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5803. Min Act: -0.1700

Data Index: 1433027 (Python Code)

Max Activating Token Index: 936

Text #4

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5738. Min Act: -0.1700

Data Index: 1578759 (Python Code)

Max Activating Token Index: 112

Text #5

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5626. Min Act: -0.1700

Data Index: 1571922 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5659. Min Act: -0.1700

Data Index: 1526360 (Python Code)

Max Activating Token Index: 540

Text #7

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1596445 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1525395 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5429. Min Act: -0.1700

Data Index: 1468552 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5306. Min Act: -0.1700

Data Index: 1365170 (Python Code)

Max Activating Token Index: 837

Text #11

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5354. Min Act: -0.1700

Data Index: 1516309 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5263. Min Act: -0.1700

Data Index: 1600393 (Python Code)

Max Activating Token Index: 853

Text #13

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5256. Min Act: -0.1700

Data Index: 1489080 (Python Code)

Max Activating Token Index: 720

Text #14

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5200. Min Act: -0.1700

Data Index: 1507213 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5251. Min Act: -0.1700

Data Index: 1586103 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5096. Min Act: -0.1700

Data Index: 1396850 (Python Code)

Max Activating Token Index: 176

Text #17

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.5064. Min Act: -0.1700

Data Index: 1437435 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.4845. Min Act: -0.1700

Data Index: 1536152 (Python Code)

Max Activating Token Index: 647

Text #19

Max Range: 3.6123. Min Range: -3.6123

Max Act: 3.4897. Min Act: -0.1700

Data Index: 1459629 (Python Code)

Max Activating Token Index: 438