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

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

Neuron 994 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: 3.4716. Min Range: -3.4716

Max Act: 3.4716. Min Act: -0.1700

Data Index: 616118 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.4246. Min Act: -0.1700

Data Index: 1493078 (Python Code)

Max Activating Token Index: 274

Text #2

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3932. Min Act: -0.1700

Data Index: 1608241 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.4246. Min Act: -0.1700

Data Index: 1413207 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3461. Min Act: -0.1700

Data Index: 46126 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3461. Min Act: -0.1700

Data Index: 1542341 (Python Code)

Max Activating Token Index: 697

Text #6

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1399259 (Python Code)

Max Activating Token Index: 176

Text #7

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3147. Min Act: -0.1700

Data Index: 1208847 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2676. Min Act: -0.1700

Data Index: 1391214 (Python Code)

Max Activating Token Index: 685

Text #9

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.3304. Min Act: -0.1700

Data Index: 1300937 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2990. Min Act: -0.1700

Data Index: 1548897 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1501403 (Python Code)

Max Activating Token Index: 731

Text #12

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1370886 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2676. Min Act: -0.1700

Data Index: 1503797 (Python Code)

Max Activating Token Index: 242

Text #14

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2833. Min Act: -0.1700

Data Index: 305827 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2676. Min Act: -0.1700

Data Index: 544206 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2362. Min Act: -0.1700

Data Index: 784097 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2519. Min Act: -0.1700

Data Index: 377539 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2362. Min Act: -0.1700

Data Index: 602758 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 3.4716. Min Range: -3.4716

Max Act: 3.2362. Min Act: -0.1700

Data Index: 1465969 (Python Code)

Max Activating Token Index: 436