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

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

Neuron 476 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: 3.7522. Min Range: -3.7522

Max Act: 3.7522. Min Act: -0.1700

Data Index: 637743 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6270. Min Act: -0.1700

Data Index: 703695 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6270. Min Act: -0.1700

Data Index: 812722 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 347761 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 687144 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6113. Min Act: -0.1700

Data Index: 1122604 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 169907 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6113. Min Act: -0.1700

Data Index: 665434 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6113. Min Act: -0.1700

Data Index: 145658 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.6113. Min Act: -0.1700

Data Index: 477598 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 562678 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5957. Min Act: -0.1700

Data Index: 694590 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1402222 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5800. Min Act: -0.1700

Data Index: 1025965 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5644. Min Act: -0.1700

Data Index: 36604 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5800. Min Act: -0.1700

Data Index: 776309 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5800. Min Act: -0.1700

Data Index: 550783 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5800. Min Act: -0.1700

Data Index: 798722 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5644. Min Act: -0.1700

Data Index: 636078 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.5644. Min Act: -0.1700

Data Index: 212753 (C4 (Web Text))

Max Activating Token Index: 16