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

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

Neuron 1406 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.6452. Min Act: -0.1700

Data Index: 107048 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.6139. Min Act: -0.1700

Data Index: 18465 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.5356. Min Act: -0.1700

Data Index: 1229607 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.5199. Min Act: -0.1700

Data Index: 717440 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.5042. Min Act: -0.1700

Data Index: 378212 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4572. Min Act: -0.1700

Data Index: 1163674 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4572. Min Act: -0.1700

Data Index: 388963 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4416. Min Act: -0.1700

Data Index: 337597 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4572. Min Act: -0.1700

Data Index: 354638 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4102. Min Act: -0.1700

Data Index: 941315 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4259. Min Act: -0.1700

Data Index: 1259604 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4416. Min Act: -0.1700

Data Index: 904497 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4102. Min Act: -0.1700

Data Index: 193406 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4102. Min Act: -0.1700

Data Index: 798028 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.4102. Min Act: -0.1700

Data Index: 2289 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.3945. Min Act: -0.1700

Data Index: 897272 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.3945. Min Act: -0.1700

Data Index: 224542 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.3788. Min Act: -0.1700

Data Index: 763416 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.3788. Min Act: -0.1700

Data Index: 1204089 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 3.6452. Min Range: -3.6452

Max Act: 3.3788. Min Act: -0.1700

Data Index: 229821 (C4 (Web Text))

Max Activating Token Index: 404