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

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

Neuron 400 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.4345. Min Act: -0.1700

Data Index: 179112 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3718. Min Act: -0.1700

Data Index: 657886 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.4032. Min Act: -0.1700

Data Index: 622071 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3718. Min Act: -0.1700

Data Index: 1046850 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3404. Min Act: -0.1700

Data Index: 471966 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3718. Min Act: -0.1700

Data Index: 1292997 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3718. Min Act: -0.1700

Data Index: 167322 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3404. Min Act: -0.1700

Data Index: 1130488 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3404. Min Act: -0.1700

Data Index: 309829 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 828470 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 414583 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 688392 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 921957 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 207008 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 891006 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 1225879 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.3090. Min Act: -0.1700

Data Index: 572884 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.2776. Min Act: -0.1700

Data Index: 207394 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.2776. Min Act: -0.1700

Data Index: 463499 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 3.4345. Min Range: -3.4345

Max Act: 3.2776. Min Act: -0.1700

Data Index: 503773 (C4 (Web Text))

Max Activating Token Index: 169