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

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

Neuron 743 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.2662. Min Act: -0.1700

Data Index: 471144 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.2033. Min Act: -0.1700

Data Index: 992799 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1876. Min Act: -0.1700

Data Index: 1610401 (Python Code)

Max Activating Token Index: 353

Text #3

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1623917 (Python Code)

Max Activating Token Index: 61

Text #4

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1613482 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0773. Min Act: -0.1700

Data Index: 1551566 (Python Code)

Max Activating Token Index: 327

Text #6

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0773. Min Act: -0.1700

Data Index: 1410680 (Python Code)

Max Activating Token Index: 702

Text #7

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0457. Min Act: -0.1700

Data Index: 1412688 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0773. Min Act: -0.1700

Data Index: 703368 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0299. Min Act: -0.1700

Data Index: 1556167 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0299. Min Act: -0.1700

Data Index: 1568212 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0299. Min Act: -0.1700

Data Index: 1381792 (Python Code)

Max Activating Token Index: 129

Text #12

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0299. Min Act: -0.1700

Data Index: 1576447 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 3.2662. Min Range: -3.2662

Max Act: 2.9825. Min Act: -0.1700

Data Index: 862337 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0141. Min Act: -0.1700

Data Index: 1614238 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0141. Min Act: -0.1700

Data Index: 1463378 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 3.2662. Min Range: -3.2662

Max Act: 2.9983. Min Act: -0.1700

Data Index: 1387150 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0141. Min Act: -0.1700

Data Index: 1455541 (Python Code)

Max Activating Token Index: 65

Text #18

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0141. Min Act: -0.1700

Data Index: 1455091 (Python Code)

Max Activating Token Index: 479

Text #19

Max Range: 3.2662. Min Range: -3.2662

Max Act: 3.0299. Min Act: -0.1700

Data Index: 1294025 (C4 (Web Text))

Max Activating Token Index: 132