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

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

Neuron 1261 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1370. Min Act: -0.1700

Data Index: 902508 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1370. Min Act: -0.1700

Data Index: 675248 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1213. Min Act: -0.1700

Data Index: 446154 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 734501 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1224833 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 370841 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1267208 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 696395 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.1055. Min Act: -0.1700

Data Index: 328626 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1226607 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0897. Min Act: -0.1700

Data Index: 1239098 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 393957 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0897. Min Act: -0.1700

Data Index: 1125869 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0897. Min Act: -0.1700

Data Index: 155262 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 1049188 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 440107 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 333914 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0582. Min Act: -0.1700

Data Index: 500913 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0582. Min Act: -0.1700

Data Index: 1100155 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 3.1370. Min Range: -3.1370

Max Act: 3.0740. Min Act: -0.1700

Data Index: 564578 (C4 (Web Text))

Max Activating Token Index: 807