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

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

Neuron 814 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: 5.0434. Min Range: -5.0434

Max Act: 5.0434. Min Act: -0.1700

Data Index: 1497257 (Python Code)

Max Activating Token Index: 243

Text #1

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.8824. Min Act: -0.1700

Data Index: 569271 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.8523. Min Act: -0.1698

Data Index: 1508870 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.7673. Min Act: -0.1696

Data Index: 497897 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.7801. Min Act: -0.1700

Data Index: 1522277 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.7454. Min Act: -0.1700

Data Index: 922199 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.7045. Min Act: -0.1700

Data Index: 717031 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.6493. Min Act: -0.1700

Data Index: 531359 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.6453. Min Act: -0.1700

Data Index: 894722 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.5974. Min Act: -0.1699

Data Index: 1071316 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.5875. Min Act: -0.1700

Data Index: 1608022 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.6065. Min Act: -0.1700

Data Index: 1528542 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.5251. Min Act: -0.1700

Data Index: 1031034 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.5248. Min Act: -0.1615

Data Index: 927335 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.4463. Min Act: -0.1699

Data Index: 855305 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.3737. Min Act: -0.1700

Data Index: 1363640 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.3746. Min Act: -0.1700

Data Index: 1483148 (Python Code)

Max Activating Token Index: 1005

Text #17

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.3619. Min Act: -0.1700

Data Index: 44077 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.3185. Min Act: -0.1700

Data Index: 1507652 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 5.0434. Min Range: -5.0434

Max Act: 4.3022. Min Act: -0.1700

Data Index: 637684 (C4 (Web Text))

Max Activating Token Index: 117