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

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

Neuron 1231 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.5589. Min Act: -0.1700

Data Index: 1085834 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.4336. Min Act: -0.1700

Data Index: 1108096 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.3081. Min Act: -0.1700

Data Index: 511639 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.3551. Min Act: -0.1700

Data Index: 1047723 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.3081. Min Act: -0.1700

Data Index: 986781 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2766. Min Act: -0.1700

Data Index: 1029845 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2923. Min Act: -0.1700

Data Index: 104094 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.3238. Min Act: -0.1700

Data Index: 803763 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2609. Min Act: -0.1700

Data Index: 1293042 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2452. Min Act: -0.1700

Data Index: 754763 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2452. Min Act: -0.1700

Data Index: 405567 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2609. Min Act: -0.1700

Data Index: 329413 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2452. Min Act: -0.1700

Data Index: 1461701 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1508. Min Act: -0.1700

Data Index: 580669 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1980. Min Act: -0.1700

Data Index: 889282 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1665. Min Act: -0.1700

Data Index: 1235209 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.2295. Min Act: -0.1700

Data Index: 621635 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1508. Min Act: -0.1700

Data Index: 859561 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1351. Min Act: -0.1700

Data Index: 905332 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 3.5589. Min Range: -3.5589

Max Act: 3.1665. Min Act: -0.1700

Data Index: 511535 (C4 (Web Text))

Max Activating Token Index: 158