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

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

Neuron 1291 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: 3.5797. Min Range: -3.5797

Max Act: 3.5797. Min Act: -0.1700

Data Index: 891845 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.5171. Min Act: -0.1700

Data Index: 194818 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.5171. Min Act: -0.1700

Data Index: 945857 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4857. Min Act: -0.1700

Data Index: 1284919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4544. Min Act: -0.1700

Data Index: 1268570 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4857. Min Act: -0.1700

Data Index: 681084 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3916. Min Act: -0.1700

Data Index: 1294496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4230. Min Act: -0.1700

Data Index: 1308683 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4230. Min Act: -0.1700

Data Index: 251387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4073. Min Act: -0.1700

Data Index: 193874 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4230. Min Act: -0.1700

Data Index: 624837 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.4073. Min Act: -0.1700

Data Index: 152210 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3916. Min Act: -0.1700

Data Index: 484441 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1359615 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3760. Min Act: -0.1700

Data Index: 1303643 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3760. Min Act: -0.1700

Data Index: 686157 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3603. Min Act: -0.1700

Data Index: 1046568 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3446. Min Act: -0.1700

Data Index: 917736 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3603. Min Act: -0.1700

Data Index: 625181 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 3.5797. Min Range: -3.5797

Max Act: 3.3760. Min Act: -0.1700

Data Index: 654049 (C4 (Web Text))

Max Activating Token Index: 509