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

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

Neuron 880 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: 3.5050. Min Range: -3.5050

Max Act: 3.5050. Min Act: -0.1700

Data Index: 589349 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1129471 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3482. Min Act: -0.1700

Data Index: 525379 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3325. Min Act: -0.1700

Data Index: 944847 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3011. Min Act: -0.1700

Data Index: 190010 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3325. Min Act: -0.1700

Data Index: 893759 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2854. Min Act: -0.1700

Data Index: 627773 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.3011. Min Act: -0.1700

Data Index: 1006300 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2854. Min Act: -0.1700

Data Index: 817661 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2854. Min Act: -0.1700

Data Index: 901717 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2539. Min Act: -0.1700

Data Index: 1297627 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2382. Min Act: -0.1700

Data Index: 248376 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2225. Min Act: -0.1700

Data Index: 1240084 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2068. Min Act: -0.1700

Data Index: 1197311 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.2068. Min Act: -0.1700

Data Index: 71061 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1077716 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.1910. Min Act: -0.1700

Data Index: 147373 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1170792 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.1910. Min Act: -0.1700

Data Index: 436808 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.5050. Min Range: -3.5050

Max Act: 3.1910. Min Act: -0.1700

Data Index: 1101115 (C4 (Web Text))

Max Activating Token Index: 196