Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 623 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.1457. Min Act: -0.1700

Data Index: 1380059 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0827. Min Act: -0.1700

Data Index: 884946 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.1142. Min Act: -0.1700

Data Index: 969927 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1181402 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0511. Min Act: -0.1700

Data Index: 654495 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0985. Min Act: -0.1700

Data Index: 1382479 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0669. Min Act: -0.1700

Data Index: 951876 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1136670 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0353. Min Act: -0.1700

Data Index: 152718 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9879. Min Act: -0.1700

Data Index: 890223 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0037. Min Act: -0.1700

Data Index: 103406 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0195. Min Act: -0.1700

Data Index: 204264 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0037. Min Act: -0.1700

Data Index: 138774 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9721. Min Act: -0.1700

Data Index: 1531736 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 3.1457. Min Range: -3.1457

Max Act: 3.0037. Min Act: -0.1700

Data Index: 78335 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9563. Min Act: -0.1700

Data Index: 541981 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9721. Min Act: -0.1700

Data Index: 14507 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9246. Min Act: -0.1700

Data Index: 1285729 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.9246. Min Act: -0.1700

Data Index: 158229 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.1457. Min Range: -3.1457

Max Act: 2.8929. Min Act: -0.1700

Data Index: 1026602 (C4 (Web Text))

Max Activating Token Index: 482