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

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

Neuron 1565 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: 3.3028. Min Range: -3.3028

Max Act: 3.3028. Min Act: -0.1700

Data Index: 528255 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1297. Min Act: -0.1700

Data Index: 187723 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 412983 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1297. Min Act: -0.1700

Data Index: 894273 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0982. Min Act: -0.1700

Data Index: 540709 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0982. Min Act: -0.1700

Data Index: 913260 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 116353 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1297. Min Act: -0.1700

Data Index: 1267402 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1068951 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 1065614 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.1140. Min Act: -0.1700

Data Index: 773271 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0667. Min Act: -0.1700

Data Index: 1117918 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0824. Min Act: -0.1700

Data Index: 59809 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0824. Min Act: -0.1700

Data Index: 357860 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0982. Min Act: -0.1700

Data Index: 805709 (C4 (Web Text))

Max Activating Token Index: 117

Text #15

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0824. Min Act: -0.1700

Data Index: 15148 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0509. Min Act: -0.1700

Data Index: 700073 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0982. Min Act: -0.1700

Data Index: 1326629 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0824. Min Act: -0.1700

Data Index: 940248 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 3.3028. Min Range: -3.3028

Max Act: 3.0824. Min Act: -0.1700

Data Index: 965648 (C4 (Web Text))

Max Activating Token Index: 680