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

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

Neuron 274 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: 3.9083. Min Range: -3.9083

Max Act: 3.9083. Min Act: -0.1699

Data Index: 336867 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8770. Min Act: -0.1700

Data Index: 215053 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8457. Min Act: -0.1700

Data Index: 1320241 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8145. Min Act: -0.1700

Data Index: 1260500 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8145. Min Act: -0.1700

Data Index: 518263 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8145. Min Act: -0.1700

Data Index: 1105176 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.8145. Min Act: -0.1700

Data Index: 1290639 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1211548 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7832. Min Act: -0.1700

Data Index: 160831 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7519. Min Act: -0.1700

Data Index: 495844 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7832. Min Act: -0.1700

Data Index: 99736 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7832. Min Act: -0.1700

Data Index: 1161395 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7519. Min Act: -0.1700

Data Index: 108601 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7519. Min Act: -0.1700

Data Index: 1006834 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7832. Min Act: -0.1700

Data Index: 743106 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7206. Min Act: -0.1700

Data Index: 801157 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7206. Min Act: -0.1700

Data Index: 444558 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7206. Min Act: -0.1700

Data Index: 960080 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.7206. Min Act: -0.1700

Data Index: 163379 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 3.9083. Min Range: -3.9083

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1217298 (C4 (Web Text))

Max Activating Token Index: 751