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

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

Neuron 1761 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: 2.8764. Min Range: -2.8764

Max Act: 2.8764. Min Act: -0.1700

Data Index: 1417368 (Python Code)

Max Activating Token Index: 841

Text #1

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.7328. Min Act: -0.1680

Data Index: 1455344 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.7111. Min Act: -0.1700

Data Index: 1582797 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6482. Min Act: -0.1700

Data Index: 1619285 (Python Code)

Max Activating Token Index: 349

Text #4

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6565. Min Act: -0.1658

Data Index: 1442029 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6493. Min Act: -0.1700

Data Index: 1480598 (Python Code)

Max Activating Token Index: 308

Text #6

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6391. Min Act: -0.1697

Data Index: 1570451 (Python Code)

Max Activating Token Index: 448

Text #7

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6168. Min Act: -0.1700

Data Index: 1452203 (Python Code)

Max Activating Token Index: 676

Text #8

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6091. Min Act: -0.1700

Data Index: 1374769 (Python Code)

Max Activating Token Index: 821

Text #9

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5956. Min Act: -0.1700

Data Index: 1416503 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5953. Min Act: -0.1684

Data Index: 1483454 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5931. Min Act: -0.1695

Data Index: 1496511 (Python Code)

Max Activating Token Index: 563

Text #12

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5879. Min Act: -0.1700

Data Index: 1422707 (Python Code)

Max Activating Token Index: 969

Text #13

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5840. Min Act: -0.1700

Data Index: 1437439 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.6020. Min Act: -0.1700

Data Index: 1495988 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5682. Min Act: -0.1699

Data Index: 1386275 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5583. Min Act: -0.1693

Data Index: 1575363 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5788. Min Act: -0.1699

Data Index: 1613891 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5731. Min Act: -0.1700

Data Index: 1545494 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 2.8764. Min Range: -2.8764

Max Act: 2.5729. Min Act: -0.1697

Data Index: 1543389 (Python Code)

Max Activating Token Index: 372