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

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

Neuron 416 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.3093. Min Act: -0.1700

Data Index: 94164 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.3250. Min Act: -0.1700

Data Index: 649887 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.2622. Min Act: -0.1700

Data Index: 605826 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.1521. Min Act: -0.1700

Data Index: 9709 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.1678. Min Act: -0.1700

Data Index: 845632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.1363. Min Act: -0.1700

Data Index: 1086688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.1363. Min Act: -0.1700

Data Index: 467166 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.1363. Min Act: -0.1700

Data Index: 884029 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0890. Min Act: -0.1700

Data Index: 613445 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0101. Min Act: -0.1700

Data Index: 229657 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0417. Min Act: -0.1700

Data Index: 584733 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0259. Min Act: -0.1700

Data Index: 1049759 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0417. Min Act: -0.1700

Data Index: 874595 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0417. Min Act: -0.1700

Data Index: 497035 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 3.3250. Min Range: -3.3250

Max Act: 2.9943. Min Act: -0.1700

Data Index: 1000731 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0259. Min Act: -0.1700

Data Index: 203332 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 3.3250. Min Range: -3.3250

Max Act: 3.0575. Min Act: -0.1700

Data Index: 997391 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 3.3250. Min Range: -3.3250

Max Act: 2.9785. Min Act: -0.1700

Data Index: 958790 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 3.3250. Min Range: -3.3250

Max Act: 2.9626. Min Act: -0.1700

Data Index: 327284 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.3250. Min Range: -3.3250

Max Act: 2.9943. Min Act: -0.1700

Data Index: 237442 (C4 (Web Text))

Max Activating Token Index: 14