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

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

Neuron 916 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: 3.4746. Min Range: -3.4746

Max Act: 3.4746. Min Act: -0.1700

Data Index: 247149 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.4119. Min Act: -0.1700

Data Index: 419987 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.4119. Min Act: -0.1700

Data Index: 345132 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3648. Min Act: -0.1700

Data Index: 90054 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.4119. Min Act: -0.1700

Data Index: 807601 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3648. Min Act: -0.1700

Data Index: 789217 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3334. Min Act: -0.1700

Data Index: 803710 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3491. Min Act: -0.1700

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3020. Min Act: -0.1700

Data Index: 793324 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 172242 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3334. Min Act: -0.1700

Data Index: 1004571 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3020. Min Act: -0.1700

Data Index: 1279400 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 807551 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3334. Min Act: -0.1700

Data Index: 1204959 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.2706. Min Act: -0.1700

Data Index: 1249709 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 1098997 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.2706. Min Act: -0.1700

Data Index: 651293 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 1331829 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 480930 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 3.4746. Min Range: -3.4746

Max Act: 3.3177. Min Act: -0.1700

Data Index: 560683 (C4 (Web Text))

Max Activating Token Index: 767