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

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

Neuron 456 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: 5.7719. Min Range: -5.7719

Max Act: 5.7719. Min Act: -0.1700

Data Index: 379404 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.6781. Min Act: -0.1700

Data Index: 1184232 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.6781. Min Act: -0.1700

Data Index: 287950 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.4906. Min Act: -0.1700

Data Index: 117382 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3969. Min Act: -0.1700

Data Index: 333707 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3969. Min Act: -0.1700

Data Index: 902398 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3344. Min Act: -0.1700

Data Index: 178426 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3031. Min Act: -0.1700

Data Index: 517960 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3344. Min Act: -0.1700

Data Index: 768702 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3344. Min Act: -0.1700

Data Index: 1238161 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3031. Min Act: -0.1700

Data Index: 209360 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3656. Min Act: -0.1700

Data Index: 260649 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3344. Min Act: -0.1700

Data Index: 539555 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3031. Min Act: -0.1700

Data Index: 109417 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.2719. Min Act: -0.1700

Data Index: 1158463 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.2094. Min Act: -0.1700

Data Index: 196415 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3031. Min Act: -0.1700

Data Index: 1148561 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.2719. Min Act: -0.1700

Data Index: 736765 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.2406. Min Act: -0.1700

Data Index: 713207 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 5.7719. Min Range: -5.7719

Max Act: 5.3031. Min Act: -0.1700

Data Index: 768125 (C4 (Web Text))

Max Activating Token Index: 355