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

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

Neuron 275 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.8689. Min Act: -0.1692

Data Index: 1104693 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5559. Min Act: -0.1700

Data Index: 1250348 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5559. Min Act: -0.1700

Data Index: 525051 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5246. Min Act: -0.1700

Data Index: 571706 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5246. Min Act: -0.1700

Data Index: 463171 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5246. Min Act: -0.1689

Data Index: 851551 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4932. Min Act: -0.1699

Data Index: 1283380 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4932. Min Act: -0.1700

Data Index: 1338239 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.5246. Min Act: -0.1700

Data Index: 492870 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1181303 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 458506 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1643

Data Index: 1179216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 845788 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1699

Data Index: 285199 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1206467 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 189933 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4305. Min Act: -0.1700

Data Index: 162426 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4305. Min Act: -0.1699

Data Index: 791073 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4619. Min Act: -0.1700

Data Index: 1076792 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 3.8689. Min Range: -3.8689

Max Act: 3.4305. Min Act: -0.1700

Data Index: 1212908 (C4 (Web Text))

Max Activating Token Index: 691