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

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

Neuron 1297 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: 5.2280. Min Range: -5.2280

Max Act: 5.2280. Min Act: -0.1700

Data Index: 908625 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.2280. Min Act: -0.1700

Data Index: 150236 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1655. Min Act: -0.1700

Data Index: 801663 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1342. Min Act: -0.1700

Data Index: 971146 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 653163 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1215828 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1339388 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1243911 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1342. Min Act: -0.1700

Data Index: 464065 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1009514 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0405. Min Act: -0.1700

Data Index: 1332528 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0717. Min Act: -0.1700

Data Index: 1121594 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1219819 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0405. Min Act: -0.1700

Data Index: 644794 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0717. Min Act: -0.1700

Data Index: 1088913 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0405. Min Act: -0.1700

Data Index: 227518 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0405. Min Act: -0.1700

Data Index: 619305 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0405. Min Act: -0.1700

Data Index: 66517 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 5.2280. Min Range: -5.2280

Max Act: 5.0092. Min Act: -0.1700

Data Index: 1014164 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 5.2280. Min Range: -5.2280

Max Act: 4.9467. Min Act: -0.1700

Data Index: 858294 (C4 (Web Text))

Max Activating Token Index: 275