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

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

Neuron 1791 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.6690. Min Act: -0.1700

Data Index: 660733 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5281. Min Act: -0.1700

Data Index: 727769 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5125. Min Act: -0.1700

Data Index: 135819 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5751. Min Act: -0.1700

Data Index: 1097706 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5281. Min Act: -0.1700

Data Index: 1026831 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5751. Min Act: -0.1700

Data Index: 236148 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.5125. Min Act: -0.1700

Data Index: 238215 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4968. Min Act: -0.1700

Data Index: 858804 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1137004 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 800026 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4341. Min Act: -0.1700

Data Index: 1078687 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4811. Min Act: -0.1700

Data Index: 16398 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 1207755 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 294055 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4341. Min Act: -0.1700

Data Index: 311640 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 816507 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 303047 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4654. Min Act: -0.1700

Data Index: 141489 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.3400. Min Act: -0.1700

Data Index: 571366 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 3.6690. Min Range: -3.6690

Max Act: 3.4341. Min Act: -0.1700

Data Index: 615084 (C4 (Web Text))

Max Activating Token Index: 78