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

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

Neuron 754 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.8068. Min Act: -0.1700

Data Index: 553872 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.8068. Min Act: -0.1700

Data Index: 1077275 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.7129. Min Act: -0.1700

Data Index: 805448 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.7442. Min Act: -0.1700

Data Index: 65905 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.7442. Min Act: -0.1700

Data Index: 1002900 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.7129. Min Act: -0.1700

Data Index: 418591 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6817. Min Act: -0.1700

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.7129. Min Act: -0.1700

Data Index: 131950 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6504. Min Act: -0.1700

Data Index: 576535 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6817. Min Act: -0.1700

Data Index: 1341768 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6504. Min Act: -0.1700

Data Index: 1248463 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6817. Min Act: -0.1700

Data Index: 213267 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.5877. Min Act: -0.1700

Data Index: 532788 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6190. Min Act: -0.1700

Data Index: 105403 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6190. Min Act: -0.1700

Data Index: 571219 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.5877. Min Act: -0.1700

Data Index: 148807 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6504. Min Act: -0.1700

Data Index: 420828 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.6504. Min Act: -0.1700

Data Index: 1084613 (C4 (Web Text))

Max Activating Token Index: 408

Text #18

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.5877. Min Act: -0.1700

Data Index: 589809 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 3.8068. Min Range: -3.8068

Max Act: 3.5877. Min Act: -0.1700

Data Index: 23384 (C4 (Web Text))

Max Activating Token Index: 551