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

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

Neuron 1324 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: 3.8560. Min Range: -3.8560

Max Act: 3.8560. Min Act: -0.1700

Data Index: 1566713 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7946. Min Act: -0.1700

Data Index: 1526058 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1389184 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7623. Min Act: -0.1700

Data Index: 1601000 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7951. Min Act: -0.1700

Data Index: 1597872 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7586. Min Act: -0.1700

Data Index: 1414946 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7255. Min Act: -0.1700

Data Index: 1394360 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7506. Min Act: -0.1699

Data Index: 1482145 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7421. Min Act: -0.1700

Data Index: 1473636 (Python Code)

Max Activating Token Index: 495

Text #9

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7060. Min Act: -0.1700

Data Index: 1435440 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6713. Min Act: -0.1700

Data Index: 1587689 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6556. Min Act: -0.1700

Data Index: 1376280 (Python Code)

Max Activating Token Index: 655

Text #12

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1476184 (Python Code)

Max Activating Token Index: 822

Text #13

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.7075. Min Act: -0.1700

Data Index: 1430289 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6868. Min Act: -0.1700

Data Index: 1594537 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6925. Min Act: -0.1700

Data Index: 1514726 (Python Code)

Max Activating Token Index: 664

Text #16

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6983. Min Act: -0.1700

Data Index: 1594279 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6695. Min Act: -0.1700

Data Index: 1496070 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6919. Min Act: -0.1700

Data Index: 1602129 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 3.8560. Min Range: -3.8560

Max Act: 3.6502. Min Act: -0.1700

Data Index: 1451122 (Python Code)

Max Activating Token Index: 494