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

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

Neuron 649 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.6055. Min Act: -0.1700

Data Index: 674021 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.5428. Min Act: -0.1700

Data Index: 85150 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.4802. Min Act: -0.1700

Data Index: 1021613 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.4488. Min Act: -0.1700

Data Index: 621029 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.4488. Min Act: -0.1700

Data Index: 503836 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.4175. Min Act: -0.1700

Data Index: 1358409 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.3076. Min Act: -0.1700

Data Index: 1205636 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.3233. Min Act: -0.1700

Data Index: 858659 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2605. Min Act: -0.1700

Data Index: 856847 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.3076. Min Act: -0.1700

Data Index: 948171 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2605. Min Act: -0.1700

Data Index: 259558 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2762. Min Act: -0.1700

Data Index: 912364 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1046084 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2605. Min Act: -0.1700

Data Index: 349248 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2762. Min Act: -0.1700

Data Index: 258626 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2605. Min Act: -0.1700

Data Index: 1077160 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1058703 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.1976. Min Act: -0.1700

Data Index: 585940 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.2448. Min Act: -0.1700

Data Index: 608808 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 3.6055. Min Range: -3.6055

Max Act: 3.1976. Min Act: -0.1700

Data Index: 225696 (C4 (Web Text))

Max Activating Token Index: 54