Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1570 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.3685. Min Act: -0.1700

Data Index: 977132 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2747. Min Act: -0.1700

Data Index: 454577 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.3060. Min Act: -0.1700

Data Index: 93446 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2435. Min Act: -0.1700

Data Index: 336878 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2435. Min Act: -0.1700

Data Index: 702159 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2122. Min Act: -0.1700

Data Index: 1325859 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2122. Min Act: -0.1700

Data Index: 1356936 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2122. Min Act: -0.1700

Data Index: 967309 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.2122. Min Act: -0.1700

Data Index: 1056240 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.1497. Min Act: -0.1700

Data Index: 440718 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.1497. Min Act: -0.1700

Data Index: 130448 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.1185. Min Act: -0.1700

Data Index: 1076092 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0559. Min Act: -0.1700

Data Index: 453255 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.1185. Min Act: -0.1700

Data Index: 1264366 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0559. Min Act: -0.1700

Data Index: 667327 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0559. Min Act: -0.1700

Data Index: 1069876 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0559. Min Act: -0.1700

Data Index: 611799 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0247. Min Act: -0.1700

Data Index: 375185 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0247. Min Act: -0.1700

Data Index: 114196 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 4.3685. Min Range: -4.3685

Max Act: 4.0247. Min Act: -0.1700

Data Index: 459939 (C4 (Web Text))

Max Activating Token Index: 316