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

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

Neuron 1877 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.2275. Min Act: -0.1700

Data Index: 594408 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.0400. Min Act: -0.1700

Data Index: 213324 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.0400. Min Act: -0.1700

Data Index: 179092 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.0400. Min Act: -0.1700

Data Index: 1101332 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.0087. Min Act: -0.1700

Data Index: 950181 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 5.2275. Min Range: -5.2275

Max Act: 5.0087. Min Act: -0.1700

Data Index: 182365 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.9462. Min Act: -0.1700

Data Index: 422831 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.9775. Min Act: -0.1700

Data Index: 139666 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.9150. Min Act: -0.1700

Data Index: 103674 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8837. Min Act: -0.1700

Data Index: 775285 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8525. Min Act: -0.1700

Data Index: 499610 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8212. Min Act: -0.1700

Data Index: 759124 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8525. Min Act: -0.1700

Data Index: 1322265 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8525. Min Act: -0.1700

Data Index: 665275 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8837. Min Act: -0.1700

Data Index: 255673 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8212. Min Act: -0.1700

Data Index: 798340 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.8212. Min Act: -0.1700

Data Index: 240164 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.7587. Min Act: -0.1700

Data Index: 1060779 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.7900. Min Act: -0.1700

Data Index: 81920 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 5.2275. Min Range: -5.2275

Max Act: 4.7900. Min Act: -0.1700

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 91