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

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

Neuron 1120 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: 5.0456. Min Range: -5.0456

Max Act: 5.0456. Min Act: -0.1700

Data Index: 478850 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 5.0456. Min Range: -5.0456

Max Act: 5.0456. Min Act: -0.1700

Data Index: 1098641 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 5.0456. Min Range: -5.0456

Max Act: 5.0456. Min Act: -0.1657

Data Index: 571321 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9831. Min Act: -0.1700

Data Index: 94464 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 954268 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.0456. Min Range: -5.0456

Max Act: 5.0143. Min Act: -0.1700

Data Index: 856367 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9518. Min Act: -0.1700

Data Index: 482857 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1691

Data Index: 170758 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 6198 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9518. Min Act: -0.1700

Data Index: 1070685 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 583442 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 828107 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 947461 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.9206. Min Act: -0.1700

Data Index: 801826 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.8581. Min Act: -0.1688

Data Index: 666349 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.8581. Min Act: -0.1700

Data Index: 885358 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.7643. Min Act: -0.1700

Data Index: 291420 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.8893. Min Act: -0.1693

Data Index: 757022 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.8268. Min Act: -0.1700

Data Index: 972132 (C4 (Web Text))

Max Activating Token Index: 848

Text #19

Max Range: 5.0456. Min Range: -5.0456

Max Act: 4.7956. Min Act: -0.1700

Data Index: 228229 (C4 (Web Text))

Max Activating Token Index: 96