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

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

Neuron 1583 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.1786. Min Act: -0.1700

Data Index: 443042 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0999. Min Act: -0.1700

Data Index: 1278636 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0999. Min Act: -0.1700

Data Index: 310021 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0683. Min Act: -0.1700

Data Index: 760473 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1297955 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0841. Min Act: -0.1700

Data Index: 489252 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0841. Min Act: -0.1700

Data Index: 622853 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0841. Min Act: -0.1700

Data Index: 809049 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0367. Min Act: -0.1700

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0209. Min Act: -0.1700

Data Index: 712469 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0683. Min Act: -0.1700

Data Index: 302876 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0367. Min Act: -0.1700

Data Index: 364837 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0051. Min Act: -0.1700

Data Index: 415919 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0209. Min Act: -0.1700

Data Index: 733146 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0367. Min Act: -0.1700

Data Index: 1133107 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0209. Min Act: -0.1700

Data Index: 1260145 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0051. Min Act: -0.1700

Data Index: 1208301 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.9893. Min Act: -0.1700

Data Index: 419527 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 3.1786. Min Range: -3.1786

Max Act: 2.9893. Min Act: -0.1700

Data Index: 1273126 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.1786. Min Range: -3.1786

Max Act: 3.0209. Min Act: -0.1700

Data Index: 1046029 (C4 (Web Text))

Max Activating Token Index: 628