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

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

Neuron 1753 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: 3.4908. Min Range: -3.4908

Max Act: 3.4908. Min Act: -0.1700

Data Index: 1556638 (Python Code)

Max Activating Token Index: 730

Text #1

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.4315. Min Act: -0.1700

Data Index: 1549806 (Python Code)

Max Activating Token Index: 849

Text #2

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.4199. Min Act: -0.1700

Data Index: 1476950 (Python Code)

Max Activating Token Index: 722

Text #3

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1650508 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3487. Min Act: -0.1700

Data Index: 1585607 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3252. Min Act: -0.1700

Data Index: 1364115 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2906. Min Act: -0.1700

Data Index: 1526179 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1500152 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3414. Min Act: -0.1700

Data Index: 1573561 (Python Code)

Max Activating Token Index: 587

Text #9

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.3287. Min Act: -0.1700

Data Index: 1440753 (Python Code)

Max Activating Token Index: 157

Text #10

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2999. Min Act: -0.1700

Data Index: 1637173 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2970. Min Act: -0.1700

Data Index: 1543210 (Python Code)

Max Activating Token Index: 419

Text #12

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2925. Min Act: -0.1700

Data Index: 614753 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1371150 (Python Code)

Max Activating Token Index: 374

Text #14

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2852. Min Act: -0.1700

Data Index: 1489768 (Python Code)

Max Activating Token Index: 559

Text #15

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2988. Min Act: -0.1700

Data Index: 1389368 (Python Code)

Max Activating Token Index: 385

Text #16

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2791. Min Act: -0.1700

Data Index: 1385707 (Python Code)

Max Activating Token Index: 865

Text #17

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2835. Min Act: -0.1700

Data Index: 243310 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2838. Min Act: -0.1700

Data Index: 1051229 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 3.4908. Min Range: -3.4908

Max Act: 3.2678. Min Act: -0.1700

Data Index: 24829 (C4 (Web Text))

Max Activating Token Index: 594