Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1238 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.9617. Min Act: -0.1700

Data Index: 1324246 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.9305. Min Act: -0.1700

Data Index: 594823 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.9305. Min Act: -0.1700

Data Index: 485010 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.9305. Min Act: -0.1700

Data Index: 43513 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 170778 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 262834 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.9305. Min Act: -0.1700

Data Index: 939215 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8679. Min Act: -0.1700

Data Index: 115069 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1076753 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1118645 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 529050 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8679. Min Act: -0.1700

Data Index: 612711 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8992. Min Act: -0.1700

Data Index: 762172 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8679. Min Act: -0.1700

Data Index: 1069511 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8679. Min Act: -0.1700

Data Index: 256242 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8367. Min Act: -0.1700

Data Index: 1509097 (Python Code)

Max Activating Token Index: 3

Text #16

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8367. Min Act: -0.1700

Data Index: 609009 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8367. Min Act: -0.1700

Data Index: 528270 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8367. Min Act: -0.1700

Data Index: 347019 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.9617. Min Range: -3.9617

Max Act: 3.8367. Min Act: -0.1700

Data Index: 183528 (C4 (Web Text))

Max Activating Token Index: 275