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

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

Neuron 1319 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: 4.3663. Min Range: -4.3663

Max Act: 4.3663. Min Act: -0.1700

Data Index: 1630151 (Python Code)

Max Activating Token Index: 235

Text #1

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.2650. Min Act: -0.1680

Data Index: 1463839 (Python Code)

Max Activating Token Index: 560

Text #2

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.2393. Min Act: -0.1687

Data Index: 1407011 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.1948. Min Act: -0.1700

Data Index: 1531955 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.1924. Min Act: -0.1700

Data Index: 1440417 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.1762. Min Act: -0.1700

Data Index: 1577858 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.1457. Min Act: -0.1699

Data Index: 1601833 (Python Code)

Max Activating Token Index: 696

Text #7

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.1070. Min Act: -0.1700

Data Index: 1404056 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0764. Min Act: -0.1699

Data Index: 1492824 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0808. Min Act: -0.1699

Data Index: 1414643 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0946. Min Act: -0.1700

Data Index: 1531771 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0857. Min Act: -0.1700

Data Index: 1543530 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0662. Min Act: -0.1700

Data Index: 227001 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0806. Min Act: -0.1700

Data Index: 1635775 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0712. Min Act: -0.1696

Data Index: 1458260 (Python Code)

Max Activating Token Index: 613

Text #15

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0585. Min Act: -0.1700

Data Index: 1529275 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0364. Min Act: -0.1700

Data Index: 1409176 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0361. Min Act: -0.1700

Data Index: 1464146 (Python Code)

Max Activating Token Index: 481

Text #18

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0240. Min Act: -0.1694

Data Index: 1561194 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 4.3663. Min Range: -4.3663

Max Act: 4.0031. Min Act: -0.1700

Data Index: 1388083 (Python Code)

Max Activating Token Index: 254