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

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

Neuron 1068 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.7400. Min Act: -0.1700

Data Index: 202267 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.6775. Min Act: -0.1700

Data Index: 1058041 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.6150. Min Act: -0.1700

Data Index: 1076691 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.5837. Min Act: -0.1700

Data Index: 142718 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.5837. Min Act: -0.1700

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.5212. Min Act: -0.1700

Data Index: 957265 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.5525. Min Act: -0.1700

Data Index: 1048207 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4900. Min Act: -0.1700

Data Index: 1274903 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4587. Min Act: -0.1700

Data Index: 1202358 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4587. Min Act: -0.1700

Data Index: 323825 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4275. Min Act: -0.1700

Data Index: 246562 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4587. Min Act: -0.1700

Data Index: 390091 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4275. Min Act: -0.1700

Data Index: 1238879 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.3962. Min Act: -0.1700

Data Index: 1336247 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.3962. Min Act: -0.1700

Data Index: 652719 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4275. Min Act: -0.1700

Data Index: 1185371 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.3962. Min Act: -0.1700

Data Index: 1152341 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.3650. Min Act: -0.1700

Data Index: 428298 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.3650. Min Act: -0.1700

Data Index: 961338 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 5.7400. Min Range: -5.7400

Max Act: 5.4275. Min Act: -0.1700

Data Index: 315126 (C4 (Web Text))

Max Activating Token Index: 991