Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1062 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0073. Min Range: -5.0073

Max Act: 5.0073. Min Act: -0.1700

Data Index: 74614 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.9448. Min Act: -0.1700

Data Index: 1018877 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.9136. Min Act: -0.1700

Data Index: 531063 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8823. Min Act: -0.1700

Data Index: 1049568 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7886. Min Act: -0.1700

Data Index: 45130 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7886. Min Act: -0.1700

Data Index: 754715 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7573. Min Act: -0.1700

Data Index: 393597 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7886. Min Act: -0.1699

Data Index: 1300507 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.8511. Min Act: -0.1700

Data Index: 343981 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7261. Min Act: -0.1700

Data Index: 398271 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7573. Min Act: -0.1700

Data Index: 397632 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.7261. Min Act: -0.1700

Data Index: 953752 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6636. Min Act: -0.1700

Data Index: 1281944 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6636. Min Act: -0.1700

Data Index: 243615 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6948. Min Act: -0.1700

Data Index: 821291 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6948. Min Act: -0.1700

Data Index: 730594 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6636. Min Act: -0.1700

Data Index: 974596 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6323. Min Act: -0.1700

Data Index: 1005165 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6323. Min Act: -0.1700

Data Index: 394410 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 5.0073. Min Range: -5.0073

Max Act: 4.6323. Min Act: -0.1700

Data Index: 182623 (C4 (Web Text))

Max Activating Token Index: 212