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

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

Neuron 1900 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: 5.6423. Min Range: -5.6423

Max Act: 5.5798. Min Act: -0.1700

Data Index: 912811 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.6423. Min Act: -0.1700

Data Index: 719045 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5173. Min Act: -0.1700

Data Index: 560480 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5173. Min Act: -0.1700

Data Index: 1004723 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5173. Min Act: -0.1700

Data Index: 547327 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5485. Min Act: -0.1700

Data Index: 704588 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4548. Min Act: -0.1700

Data Index: 596852 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5173. Min Act: -0.1700

Data Index: 694054 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4860. Min Act: -0.1700

Data Index: 153765 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5173. Min Act: -0.1700

Data Index: 78264 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4548. Min Act: -0.1700

Data Index: 643609 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.3923. Min Act: -0.1700

Data Index: 431275 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4235. Min Act: -0.1700

Data Index: 683315 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4860. Min Act: -0.1700

Data Index: 913907 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4235. Min Act: -0.1700

Data Index: 904906 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.3923. Min Act: -0.1700

Data Index: 1072049 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.3298. Min Act: -0.1700

Data Index: 10224 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.3923. Min Act: -0.1700

Data Index: 1061696 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4235. Min Act: -0.1700

Data Index: 1123307 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.4235. Min Act: -0.1700

Data Index: 641171 (C4 (Web Text))

Max Activating Token Index: 439