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

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

Neuron 1205 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0114. Min Range: -3.0114

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1338140 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 3.0114. Min Range: -3.0114

Max Act: 3.0114. Min Act: -0.1700

Data Index: 847582 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9639. Min Act: -0.1700

Data Index: 1138042 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8847. Min Act: -0.1700

Data Index: 1265043 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9639. Min Act: -0.1700

Data Index: 135745 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9323. Min Act: -0.1700

Data Index: 697198 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9323. Min Act: -0.1700

Data Index: 1018664 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9323. Min Act: -0.1700

Data Index: 97517 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9323. Min Act: -0.1700

Data Index: 1084396 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9005. Min Act: -0.1700

Data Index: 864019 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9005. Min Act: -0.1700

Data Index: 826892 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9639. Min Act: -0.1700

Data Index: 850060 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8847. Min Act: -0.1700

Data Index: 263306 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8688. Min Act: -0.1700

Data Index: 1282318 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8370. Min Act: -0.1700

Data Index: 707173 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9005. Min Act: -0.1700

Data Index: 721619 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9323. Min Act: -0.1700

Data Index: 288617 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.9797. Min Act: -0.1700

Data Index: 1355392 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8847. Min Act: -0.1700

Data Index: 725898 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 3.0114. Min Range: -3.0114

Max Act: 2.8847. Min Act: -0.1700

Data Index: 505621 (C4 (Web Text))

Max Activating Token Index: 620