Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1182 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.5414. Min Act: -0.1700

Data Index: 1103954 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.5414. Min Act: -0.1700

Data Index: 598325 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.5414. Min Act: -0.1700

Data Index: 740418 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.6039. Min Act: -0.1700

Data Index: 1033251 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 976458 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 1269832 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 259478 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 1140579 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 1077671 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 1075520 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.5414. Min Act: -0.1700

Data Index: 272870 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4789. Min Act: -0.1700

Data Index: 1340116 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4164. Min Act: -0.1700

Data Index: 290068 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4164. Min Act: -0.1700

Data Index: 505363 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4164. Min Act: -0.1700

Data Index: 240709 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.4164. Min Act: -0.1700

Data Index: 253120 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.3539. Min Act: -0.1700

Data Index: 768118 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.3539. Min Act: -0.1700

Data Index: 6311 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.3539. Min Act: -0.1700

Data Index: 664307 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 7.6039. Min Range: -7.6039

Max Act: 7.3539. Min Act: -0.1700

Data Index: 1253287 (C4 (Web Text))

Max Activating Token Index: 579