Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1508 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.8570. Min Act: -0.1700

Data Index: 1310295 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.8570. Min Act: -0.1700

Data Index: 255087 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.7633. Min Act: -0.1700

Data Index: 1090219 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.7320. Min Act: -0.1700

Data Index: 1228142 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.7008. Min Act: -0.1700

Data Index: 658798 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.6695. Min Act: -0.1700

Data Index: 985385 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.6695. Min Act: -0.1700

Data Index: 796621 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.6070. Min Act: -0.1700

Data Index: 664816 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5758. Min Act: -0.1700

Data Index: 364712 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.6070. Min Act: -0.1700

Data Index: 1335704 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.6070. Min Act: -0.1700

Data Index: 412448 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5445. Min Act: -0.1700

Data Index: 292213 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5445. Min Act: -0.1700

Data Index: 1012994 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.4820. Min Act: -0.1700

Data Index: 1333837 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5445. Min Act: -0.1700

Data Index: 693516 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.4820. Min Act: -0.1700

Data Index: 649735 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.4820. Min Act: -0.1700

Data Index: 123051 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5133. Min Act: -0.1700

Data Index: 183914 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5758. Min Act: -0.1700

Data Index: 808296 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 5.8570. Min Range: -5.8570

Max Act: 5.5445. Min Act: -0.1700

Data Index: 256160 (C4 (Web Text))

Max Activating Token Index: 58