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

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

Neuron 1128 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: 5.6323. Min Range: -5.6323

Max Act: 5.6323. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4760. Min Act: -0.1700

Data Index: 749935 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 1352548 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 98817 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.4448. Min Act: -0.1700

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3823. Min Act: -0.1700

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3823. Min Act: -0.1700

Data Index: 248455 (C4 (Web Text))

Max Activating Token Index: 539

Text #7

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 546229 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 1169283 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.3198. Min Act: -0.1700

Data Index: 943919 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.1635. Min Act: -0.1700

Data Index: 939772 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.1635. Min Act: -0.1700

Data Index: 1211641 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.1948. Min Act: -0.1700

Data Index: 484944 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.1010. Min Act: -0.1700

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.2260. Min Act: -0.1700

Data Index: 896920 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.1323. Min Act: -0.1700

Data Index: 445221 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.0698. Min Act: -0.1700

Data Index: 309372 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.0698. Min Act: -0.1700

Data Index: 269743 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.0073. Min Act: -0.1699

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 5.6323. Min Range: -5.6323

Max Act: 5.0073. Min Act: -0.1700

Data Index: 509439 (C4 (Web Text))

Max Activating Token Index: 445