Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1268 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.1076. Min Act: -0.1700

Data Index: 134813 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.0855. Min Act: -0.1700

Data Index: 546118 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.1076. Min Range: -3.1076

Max Act: 3.0682. Min Act: -0.1700

Data Index: 5315 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9508. Min Act: -0.1700

Data Index: 195616 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9977. Min Act: -0.1700

Data Index: 229208 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9915. Min Act: -0.1700

Data Index: 797259 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9952. Min Act: -0.1700

Data Index: 579081 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9686. Min Act: -0.1700

Data Index: 273842 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9688. Min Act: -0.1700

Data Index: 577537 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9758. Min Act: -0.1700

Data Index: 342462 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9347. Min Act: -0.1700

Data Index: 1222842 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9451. Min Act: -0.1700

Data Index: 161821 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9629. Min Act: -0.1700

Data Index: 350174 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9512. Min Act: -0.1700

Data Index: 1073479 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9099. Min Act: -0.1700

Data Index: 267205 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.9015. Min Act: -0.1700

Data Index: 1078844 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.8768. Min Act: -0.1700

Data Index: 300662 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.8717. Min Act: -0.1700

Data Index: 1063864 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.8802. Min Act: -0.1700

Data Index: 1005413 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 3.1076. Min Range: -3.1076

Max Act: 2.8742. Min Act: -0.1700

Data Index: 554133 (C4 (Web Text))

Max Activating Token Index: 36