Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 487 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.2354. Min Act: -0.1700

Data Index: 770086 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0791. Min Act: -0.1700

Data Index: 809282 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.1416. Min Act: -0.1700

Data Index: 234650 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0479. Min Act: -0.1700

Data Index: 102431 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0479. Min Act: -0.1700

Data Index: 1229776 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9541. Min Act: -0.1700

Data Index: 2704 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0479. Min Act: -0.1700

Data Index: 732061 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0479. Min Act: -0.1700

Data Index: 120839 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9854. Min Act: -0.1700

Data Index: 1124086 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9541. Min Act: -0.1700

Data Index: 889850 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9854. Min Act: -0.1700

Data Index: 1256649 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.8916. Min Act: -0.1700

Data Index: 619068 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9541. Min Act: -0.1700

Data Index: 671133 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.8448. Min Act: -0.1700

Data Index: 725995 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9229. Min Act: -0.1700

Data Index: 1257989 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.8604. Min Act: -0.1700

Data Index: 290203 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.8916. Min Act: -0.1700

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.9229. Min Act: -0.1700

Data Index: 107370 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 5.2354. Min Range: -5.2354

Max Act: 5.0166. Min Act: -0.1700

Data Index: 963202 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 5.2354. Min Range: -5.2354

Max Act: 4.8604. Min Act: -0.1700

Data Index: 588435 (C4 (Web Text))

Max Activating Token Index: 993