Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1069 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3231. Min Range: -5.3231

Max Act: 5.3231. Min Act: -0.1700

Data Index: 1327043 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 5.3231. Min Range: -5.3231

Max Act: 5.1044. Min Act: -0.1700

Data Index: 640121 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 5.3231. Min Range: -5.3231

Max Act: 5.0106. Min Act: -0.1700

Data Index: 1153838 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 5.3231. Min Range: -5.3231

Max Act: 5.0106. Min Act: -0.1700

Data Index: 241682 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.8856. Min Act: -0.1700

Data Index: 486028 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.8544. Min Act: -0.1700

Data Index: 344756 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.8231. Min Act: -0.1700

Data Index: 1168136 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.7294. Min Act: -0.1700

Data Index: 114852 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.7919. Min Act: -0.1700

Data Index: 150250 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.7919. Min Act: -0.1700

Data Index: 894037 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6981. Min Act: -0.1700

Data Index: 513154 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6981. Min Act: -0.1700

Data Index: 741262 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.7294. Min Act: -0.1699

Data Index: 475150 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6981. Min Act: -0.1700

Data Index: 1000127 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6669. Min Act: -0.1700

Data Index: 535246 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6981. Min Act: -0.1700

Data Index: 381960 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6044. Min Act: -0.1700

Data Index: 189630 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6669. Min Act: -0.1700

Data Index: 588373 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6669. Min Act: -0.1700

Data Index: 183871 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 5.3231. Min Range: -5.3231

Max Act: 4.6044. Min Act: -0.1700

Data Index: 1340566 (C4 (Web Text))

Max Activating Token Index: 186