Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1855 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.4341. Min Act: -0.1700

Data Index: 1411027 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.4184. Min Act: -0.1700

Data Index: 1451780 (Python Code)

Max Activating Token Index: 810

Text #2

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.4027. Min Act: -0.1700

Data Index: 1649074 (Python Code)

Max Activating Token Index: 471

Text #3

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.4027. Min Act: -0.1700

Data Index: 1398777 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.3870. Min Act: -0.1700

Data Index: 1597859 (Python Code)

Max Activating Token Index: 337

Text #5

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.3713. Min Act: -0.1700

Data Index: 1488746 (Python Code)

Max Activating Token Index: 421

Text #6

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1423154 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.3399. Min Act: -0.1700

Data Index: 1586697 (Python Code)

Max Activating Token Index: 422

Text #8

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2771. Min Act: -0.1700

Data Index: 1405678 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1529340 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2928. Min Act: -0.1700

Data Index: 1487610 (Python Code)

Max Activating Token Index: 706

Text #11

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2457. Min Act: -0.1700

Data Index: 1562368 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2457. Min Act: -0.1700

Data Index: 1453964 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1516685 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1575859 (Python Code)

Max Activating Token Index: 1007

Text #15

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.2142. Min Act: -0.1700

Data Index: 1506790 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1460199 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.1513. Min Act: -0.1700

Data Index: 1497553 (Python Code)

Max Activating Token Index: 569

Text #18

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.1040. Min Act: -0.1700

Data Index: 1561583 (Python Code)

Max Activating Token Index: 569

Text #19

Max Range: 3.4341. Min Range: -3.4341

Max Act: 3.0882. Min Act: -0.1700

Data Index: 1360732 (Python Code)

Max Activating Token Index: 689