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

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

Neuron 1532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0816. Min Range: -5.0816

Max Act: 5.0816. Min Act: -0.1700

Data Index: 1333250 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.0816. Min Range: -5.0816

Max Act: 5.0191. Min Act: -0.1700

Data Index: 601192 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.9878. Min Act: -0.1700

Data Index: 1082416 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8941. Min Act: -0.1700

Data Index: 26569 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.9566. Min Act: -0.1700

Data Index: 846690 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.9253. Min Act: -0.1700

Data Index: 456715 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.9253. Min Act: -0.1700

Data Index: 505478 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8941. Min Act: -0.1700

Data Index: 127579 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8941. Min Act: -0.1700

Data Index: 1179545 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8628. Min Act: -0.1700

Data Index: 1191277 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8316. Min Act: -0.1700

Data Index: 295981 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8316. Min Act: -0.1700

Data Index: 1266045 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8003. Min Act: -0.1700

Data Index: 177382 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8316. Min Act: -0.1700

Data Index: 171227 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.7691. Min Act: -0.1700

Data Index: 1197909 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.8003. Min Act: -0.1700

Data Index: 454653 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.7066. Min Act: -0.1700

Data Index: 813958 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.7378. Min Act: -0.1700

Data Index: 1061435 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.7378. Min Act: -0.1700

Data Index: 936446 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 5.0816. Min Range: -5.0816

Max Act: 4.7691. Min Act: -0.1700

Data Index: 573564 (C4 (Web Text))

Max Activating Token Index: 475