Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1619 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.6110. Min Act: -0.1700

Data Index: 1338515 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5954. Min Act: -0.1700

Data Index: 720258 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.6110. Min Act: -0.1700

Data Index: 1030155 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5954. Min Act: -0.1700

Data Index: 483761 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5797. Min Act: -0.1700

Data Index: 847518 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5641. Min Act: -0.1700

Data Index: 737903 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5797. Min Act: -0.1700

Data Index: 732955 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5641. Min Act: -0.1700

Data Index: 463074 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 324353 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5641. Min Act: -0.1700

Data Index: 774341 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 302742 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5327. Min Act: -0.1700

Data Index: 132769 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 1025914 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 492617 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 917965 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5484. Min Act: -0.1700

Data Index: 242691 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5327. Min Act: -0.1700

Data Index: 467358 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5327. Min Act: -0.1700

Data Index: 524297 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 3.6110. Min Range: -3.6110

Max Act: 3.5327. Min Act: -0.1700

Data Index: 666642 (C4 (Web Text))

Max Activating Token Index: 125