Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3647. Min Act: -0.1700

Data Index: 1448927 (Python Code)

Max Activating Token Index: 354

Text #1

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.3019. Min Act: -0.1700

Data Index: 1370316 (Python Code)

Max Activating Token Index: 566

Text #2

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 169767 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2862. Min Act: -0.1700

Data Index: 1576417 (Python Code)

Max Activating Token Index: 516

Text #4

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1520792 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1488395 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1390797 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1592092 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2548. Min Act: -0.1700

Data Index: 1648667 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1429561 (Python Code)

Max Activating Token Index: 696

Text #10

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1612000 (Python Code)

Max Activating Token Index: 434

Text #11

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1373352 (Python Code)

Max Activating Token Index: 349

Text #12

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2705. Min Act: -0.1700

Data Index: 1359894 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1415747 (Python Code)

Max Activating Token Index: 786

Text #14

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1425780 (Python Code)

Max Activating Token Index: 650

Text #15

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1652208 (Python Code)

Max Activating Token Index: 838

Text #16

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1410455 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1542061 (Python Code)

Max Activating Token Index: 643

Text #18

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2076. Min Act: -0.1700

Data Index: 1531907 (Python Code)

Max Activating Token Index: 539

Text #19

Max Range: 3.3647. Min Range: -3.3647

Max Act: 3.2391. Min Act: -0.1700

Data Index: 1602695 (Python Code)

Max Activating Token Index: 371