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

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

Neuron 788 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.4745. Min Act: -0.1700

Data Index: 1473606 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.3807. Min Act: -0.1700

Data Index: 1366847 (Python Code)

Max Activating Token Index: 567

Text #2

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.3495. Min Act: -0.1700

Data Index: 1440337 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.2870. Min Act: -0.1700

Data Index: 1433347 (Python Code)

Max Activating Token Index: 176

Text #4

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.3495. Min Act: -0.1700

Data Index: 1635173 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.2870. Min Act: -0.1700

Data Index: 1458230 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.2557. Min Act: -0.1700

Data Index: 1582460 (Python Code)

Max Activating Token Index: 24

Text #7

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.2557. Min Act: -0.1700

Data Index: 1464272 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1932. Min Act: -0.1700

Data Index: 1427547 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1932. Min Act: -0.1700

Data Index: 1490865 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1620. Min Act: -0.1700

Data Index: 1560953 (Python Code)

Max Activating Token Index: 425

Text #11

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1307. Min Act: -0.1700

Data Index: 1555748 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.0995. Min Act: -0.1700

Data Index: 1438190 (Python Code)

Max Activating Token Index: 32

Text #13

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.0995. Min Act: -0.1700

Data Index: 1478209 (Python Code)

Max Activating Token Index: 156

Text #14

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1307. Min Act: -0.1700

Data Index: 1547403 (Python Code)

Max Activating Token Index: 136

Text #15

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1307. Min Act: -0.1700

Data Index: 1567973 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.0682. Min Act: -0.1700

Data Index: 1506300 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1620. Min Act: -0.1700

Data Index: 1539646 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.1620. Min Act: -0.1700

Data Index: 1418349 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 5.4745. Min Range: -5.4745

Max Act: 5.0682. Min Act: -0.1700

Data Index: 1536157 (Python Code)

Max Activating Token Index: 29