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

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

Neuron 1115 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: 3.7040. Min Range: -3.7040

Max Act: 3.7040. Min Act: -0.1700

Data Index: 1475207 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6830. Min Act: -0.1700

Data Index: 1467145 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6088. Min Act: -0.1700

Data Index: 1480587 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5753. Min Act: -0.1700

Data Index: 1435417 (Python Code)

Max Activating Token Index: 575

Text #4

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.6000. Min Act: -0.1700

Data Index: 1545330 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5712. Min Act: -0.1700

Data Index: 1395192 (Python Code)

Max Activating Token Index: 238

Text #6

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5758. Min Act: -0.1700

Data Index: 1580960 (Python Code)

Max Activating Token Index: 254

Text #7

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5837. Min Act: -0.1700

Data Index: 1457270 (Python Code)

Max Activating Token Index: 831

Text #8

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5505. Min Act: -0.1700

Data Index: 1646506 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5230. Min Act: -0.1700

Data Index: 1556963 (Python Code)

Max Activating Token Index: 844

Text #10

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5091. Min Act: -0.1700

Data Index: 1375085 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4883. Min Act: -0.1700

Data Index: 1413979 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5037. Min Act: -0.1700

Data Index: 1474495 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.5119. Min Act: -0.1700

Data Index: 1593454 (Python Code)

Max Activating Token Index: 696

Text #14

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4804. Min Act: -0.1700

Data Index: 1621367 (Python Code)

Max Activating Token Index: 669

Text #15

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1415586 (Python Code)

Max Activating Token Index: 412

Text #16

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4524. Min Act: -0.1700

Data Index: 1549114 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4558. Min Act: -0.1700

Data Index: 1531223 (Python Code)

Max Activating Token Index: 457

Text #18

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1438643 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 3.7040. Min Range: -3.7040

Max Act: 3.4802. Min Act: -0.1700

Data Index: 1581212 (Python Code)

Max Activating Token Index: 932