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

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

Neuron 1138 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: 3.2943. Min Range: -3.2943

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1587800 (Python Code)

Max Activating Token Index: 591

Text #1

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.2000. Min Act: -0.1700

Data Index: 1442732 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.2000. Min Act: -0.1700

Data Index: 1636748 (Python Code)

Max Activating Token Index: 677

Text #3

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1370. Min Act: -0.1700

Data Index: 507536 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1528. Min Act: -0.1700

Data Index: 1076512 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1370. Min Act: -0.1700

Data Index: 22719 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1370. Min Act: -0.1700

Data Index: 236886 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1213. Min Act: -0.1700

Data Index: 778969 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1370. Min Act: -0.1700

Data Index: 80715 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1479030 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.1055. Min Act: -0.1700

Data Index: 1609084 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0897. Min Act: -0.1700

Data Index: 72320 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0582. Min Act: -0.1700

Data Index: 849142 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0582. Min Act: -0.1700

Data Index: 136660 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0582. Min Act: -0.1700

Data Index: 971813 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0582. Min Act: -0.1700

Data Index: 256784 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0424. Min Act: -0.1700

Data Index: 794004 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0108. Min Act: -0.1700

Data Index: 413161 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0108. Min Act: -0.1700

Data Index: 154356 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 3.2943. Min Range: -3.2943

Max Act: 3.0108. Min Act: -0.1700

Data Index: 1129313 (C4 (Web Text))

Max Activating Token Index: 60