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

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

Neuron 73 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: 3.2181. Min Range: -3.2181

Max Act: 3.2181. Min Act: -0.1700

Data Index: 969576 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1866. Min Act: -0.1700

Data Index: 725108 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0921. Min Act: -0.1700

Data Index: 105482 (C4 (Web Text))

Max Activating Token Index: 606

Text #3

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.2024. Min Act: -0.1700

Data Index: 449511 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1552. Min Act: -0.1700

Data Index: 399404 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1394. Min Act: -0.1700

Data Index: 1211374 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1394. Min Act: -0.1700

Data Index: 1266710 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1079. Min Act: -0.1700

Data Index: 1262152 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1394. Min Act: -0.1700

Data Index: 844260 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1237. Min Act: -0.1700

Data Index: 9552 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0764. Min Act: -0.1700

Data Index: 1126248 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1237. Min Act: -0.1700

Data Index: 917247 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1394. Min Act: -0.1700

Data Index: 911594 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1079. Min Act: -0.1700

Data Index: 218319 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1079. Min Act: -0.1700

Data Index: 784856 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.1552. Min Act: -0.1700

Data Index: 1013929 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0921. Min Act: -0.1700

Data Index: 294200 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0921. Min Act: -0.1700

Data Index: 605207 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0764. Min Act: -0.1700

Data Index: 820337 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 3.2181. Min Range: -3.2181

Max Act: 3.0764. Min Act: -0.1700

Data Index: 22201 (C4 (Web Text))

Max Activating Token Index: 477