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

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

Neuron 1823 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: 2.9584. Min Range: -2.9584

Max Act: 2.9584. Min Act: -0.1700

Data Index: 164639 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7816. Min Act: -0.1700

Data Index: 186614 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7886. Min Act: -0.1700

Data Index: 603950 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7717. Min Act: -0.1700

Data Index: 1241765 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7746. Min Act: -0.1700

Data Index: 143993 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7730. Min Act: -0.1700

Data Index: 505477 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7612. Min Act: -0.1700

Data Index: 1138370 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7619. Min Act: -0.1698

Data Index: 1260199 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7529. Min Act: -0.1700

Data Index: 338749 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7499. Min Act: -0.1700

Data Index: 1060744 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7131. Min Act: -0.1700

Data Index: 1027997 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7203. Min Act: -0.1700

Data Index: 801625 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7151. Min Act: -0.1700

Data Index: 214003 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7057. Min Act: -0.1700

Data Index: 231282 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7082. Min Act: -0.1700

Data Index: 1273627 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7123. Min Act: -0.1700

Data Index: 1346069 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7045. Min Act: -0.1700

Data Index: 737205 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.6960. Min Act: -0.1695

Data Index: 404515 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.7036. Min Act: -0.1700

Data Index: 955941 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 2.9584. Min Range: -2.9584

Max Act: 2.6954. Min Act: -0.1700

Data Index: 676257 (C4 (Web Text))

Max Activating Token Index: 421