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

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

Neuron 1293 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.4580. Min Act: -0.1700

Data Index: 420860 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.4266. Min Act: -0.1700

Data Index: 359031 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.4109. Min Act: -0.1700

Data Index: 1092136 (C4 (Web Text))

Max Activating Token Index: 333

Text #3

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.4423. Min Act: -0.1700

Data Index: 1280174 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3952. Min Act: -0.1700

Data Index: 209034 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3795. Min Act: -0.1700

Data Index: 915986 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3795. Min Act: -0.1700

Data Index: 234500 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3168. Min Act: -0.1700

Data Index: 1007218 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3011. Min Act: -0.1700

Data Index: 503020 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.3168. Min Act: -0.1700

Data Index: 296810 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2696. Min Act: -0.1700

Data Index: 778391 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2854. Min Act: -0.1700

Data Index: 392911 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2854. Min Act: -0.1700

Data Index: 404048 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2539. Min Act: -0.1700

Data Index: 313638 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2539. Min Act: -0.1700

Data Index: 585349 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2539. Min Act: -0.1700

Data Index: 189530 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2225. Min Act: -0.1700

Data Index: 1162922 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2539. Min Act: -0.1700

Data Index: 784770 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2382. Min Act: -0.1700

Data Index: 1019243 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 3.4580. Min Range: -3.4580

Max Act: 3.2225. Min Act: -0.1700

Data Index: 550413 (C4 (Web Text))

Max Activating Token Index: 588