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

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

Neuron 159 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: 3.5563. Min Range: -3.5563

Max Act: 3.5563. Min Act: -0.1700

Data Index: 1065298 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.4425. Min Act: -0.1700

Data Index: 1023741 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.4225. Min Act: -0.1700

Data Index: 1381290 (Python Code)

Max Activating Token Index: 761

Text #3

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.4029. Min Act: -0.1700

Data Index: 1591969 (Python Code)

Max Activating Token Index: 488

Text #4

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.4113. Min Act: -0.1700

Data Index: 1010457 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3893. Min Act: -0.1700

Data Index: 1048867 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3736. Min Act: -0.1700

Data Index: 1653915 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3784. Min Act: -0.1700

Data Index: 1557958 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3999. Min Act: -0.1700

Data Index: 1382402 (Python Code)

Max Activating Token Index: 971

Text #9

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3940. Min Act: -0.1700

Data Index: 844356 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.4025. Min Act: -0.1700

Data Index: 671635 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3440. Min Act: -0.1700

Data Index: 545847 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3371. Min Act: -0.1700

Data Index: 1515114 (Python Code)

Max Activating Token Index: 539

Text #13

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3227. Min Act: -0.1700

Data Index: 286769 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3402. Min Act: -0.1700

Data Index: 1312055 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3455. Min Act: -0.1700

Data Index: 319362 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3099. Min Act: -0.1700

Data Index: 1623281 (Python Code)

Max Activating Token Index: 684

Text #17

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3454. Min Act: -0.1700

Data Index: 933301 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1502986 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 3.5563. Min Range: -3.5563

Max Act: 3.3177. Min Act: -0.1700

Data Index: 1162032 (C4 (Web Text))

Max Activating Token Index: 484