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

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

Neuron 248 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: 4.8508. Min Range: -4.8508

Max Act: 4.8508. Min Act: -0.1700

Data Index: 483858 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.6340. Min Act: -0.1700

Data Index: 1418030 (Python Code)

Max Activating Token Index: 440

Text #2

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.6555. Min Act: -0.1700

Data Index: 1648758 (Python Code)

Max Activating Token Index: 703

Text #3

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.6029. Min Act: -0.1700

Data Index: 1505357 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.6164. Min Act: -0.1700

Data Index: 1019388 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.6026. Min Act: -0.1700

Data Index: 648033 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5631. Min Act: -0.1700

Data Index: 1647760 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5596. Min Act: -0.1700

Data Index: 1604963 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5641. Min Act: -0.1700

Data Index: 808162 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5748. Min Act: -0.1700

Data Index: 773388 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5217. Min Act: -0.1700

Data Index: 53601 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5395. Min Act: -0.1700

Data Index: 1562212 (Python Code)

Max Activating Token Index: 774

Text #12

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5333. Min Act: -0.1700

Data Index: 1216169 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5182. Min Act: -0.1700

Data Index: 1292794 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5451. Min Act: -0.1700

Data Index: 394143 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5345. Min Act: -0.1699

Data Index: 1041177 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.4934. Min Act: -0.1700

Data Index: 533795 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.4952. Min Act: -0.1700

Data Index: 1629491 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.4785. Min Act: -0.1700

Data Index: 1516100 (Python Code)

Max Activating Token Index: 279

Text #19

Max Range: 4.8508. Min Range: -4.8508

Max Act: 4.5077. Min Act: -0.1700

Data Index: 1512353 (Python Code)

Max Activating Token Index: 977