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

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

Neuron 1729 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: 5.2586. Min Range: -5.2586

Max Act: 5.2586. Min Act: -0.1700

Data Index: 667139 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.1649. Min Act: -0.1700

Data Index: 1233325 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.1649. Min Act: -0.1700

Data Index: 142265 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.1336. Min Act: -0.1700

Data Index: 1342077 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.1024. Min Act: -0.1700

Data Index: 1093800 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0711. Min Act: -0.1700

Data Index: 546174 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0711. Min Act: -0.1700

Data Index: 1061844 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0711. Min Act: -0.1700

Data Index: 839828 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 880502 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 339641 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 1185102 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 236612 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0711. Min Act: -0.1700

Data Index: 617030 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 890411 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0711. Min Act: -0.1700

Data Index: 1058267 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 1139192 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 386435 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0399. Min Act: -0.1700

Data Index: 1182007 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0086. Min Act: -0.1700

Data Index: 245260 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 5.2586. Min Range: -5.2586

Max Act: 5.0086. Min Act: -0.1700

Data Index: 1257789 (C4 (Web Text))

Max Activating Token Index: 755