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

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

Neuron 633 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.6420. Min Act: -0.1700

Data Index: 67505 (C4 (Web Text))

Max Activating Token Index: 693

Text #1

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5794. Min Act: -0.1700

Data Index: 173479 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5794. Min Act: -0.1700

Data Index: 967746 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 669539 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 1060119 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 673917 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 273174 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 1214696 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 861616 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 459649 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 1309821 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5011. Min Act: -0.1700

Data Index: 131701 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 100947 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5481. Min Act: -0.1700

Data Index: 867806 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5011. Min Act: -0.1700

Data Index: 770655 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1444317 (Python Code)

Max Activating Token Index: 651

Text #16

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.5167. Min Act: -0.1700

Data Index: 1629619 (Python Code)

Max Activating Token Index: 484

Text #17

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4854. Min Act: -0.1700

Data Index: 523148 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4854. Min Act: -0.1700

Data Index: 758233 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.6420. Min Range: -3.6420

Max Act: 3.4854. Min Act: -0.1700

Data Index: 340295 (C4 (Web Text))

Max Activating Token Index: 846