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

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

Neuron 1028 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: 3.0198. Min Range: -3.0198

Max Act: 3.0198. Min Act: -0.1700

Data Index: 716042 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9407. Min Act: -0.1700

Data Index: 412463 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.9090. Min Act: -0.1700

Data Index: 4271 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8614. Min Act: -0.1700

Data Index: 798151 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8455. Min Act: -0.1700

Data Index: 14784 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8296. Min Act: -0.1700

Data Index: 603660 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8137. Min Act: -0.1700

Data Index: 693438 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7978. Min Act: -0.1700

Data Index: 577276 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8296. Min Act: -0.1700

Data Index: 1001921 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.8296. Min Act: -0.1700

Data Index: 622826 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7818. Min Act: -0.1700

Data Index: 209613 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7978. Min Act: -0.1700

Data Index: 1315978 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7659. Min Act: -0.1700

Data Index: 822824 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7659. Min Act: -0.1700

Data Index: 1126588 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7818. Min Act: -0.1700

Data Index: 1102025 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7659. Min Act: -0.1700

Data Index: 1037753 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7659. Min Act: -0.1700

Data Index: 435691 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7818. Min Act: -0.1700

Data Index: 752860 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7659. Min Act: -0.1700

Data Index: 1099531 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 3.0198. Min Range: -3.0198

Max Act: 2.7499. Min Act: -0.1700

Data Index: 242412 (C4 (Web Text))

Max Activating Token Index: 45