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

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

Neuron 149 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: 5.1408. Min Range: -5.1408

Max Act: 5.1408. Min Act: -0.1699

Data Index: 79926 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 5.1408. Min Range: -5.1408

Max Act: 5.0783. Min Act: -0.1700

Data Index: 1269965 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9846. Min Act: -0.1700

Data Index: 872462 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9221. Min Act: -0.1700

Data Index: 1063232 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8908. Min Act: -0.1700

Data Index: 184953 (C4 (Web Text))

Max Activating Token Index: 657

Text #5

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9221. Min Act: -0.1700

Data Index: 85313 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9221. Min Act: -0.1699

Data Index: 542670 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8908. Min Act: -0.1700

Data Index: 1185889 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9533. Min Act: -0.1700

Data Index: 6119 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8596. Min Act: -0.1700

Data Index: 349887 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8908. Min Act: -0.1700

Data Index: 793798 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8908. Min Act: -0.1700

Data Index: 568232 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.9533. Min Act: -0.1700

Data Index: 982167 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8908. Min Act: -0.1700

Data Index: 519852 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8596. Min Act: -0.1700

Data Index: 773647 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8283. Min Act: -0.1700

Data Index: 1211231 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8283. Min Act: -0.1700

Data Index: 176353 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.7971. Min Act: -0.1700

Data Index: 595314 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.7658. Min Act: -0.1700

Data Index: 502737 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 5.1408. Min Range: -5.1408

Max Act: 4.8283. Min Act: -0.1700

Data Index: 774435 (C4 (Web Text))

Max Activating Token Index: 800