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

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

Neuron 1273 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: 3.5938. Min Range: -3.5938

Max Act: 3.5938. Min Act: -0.1700

Data Index: 932115 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.4058. Min Act: -0.1700

Data Index: 1291319 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.4058. Min Act: -0.1700

Data Index: 498068 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.3744. Min Act: -0.1700

Data Index: 631286 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.3116. Min Act: -0.1700

Data Index: 1119757 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2802. Min Act: -0.1700

Data Index: 1049680 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.3430. Min Act: -0.1700

Data Index: 635759 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2488. Min Act: -0.1700

Data Index: 372418 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2802. Min Act: -0.1700

Data Index: 623845 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2802. Min Act: -0.1700

Data Index: 136062 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2488. Min Act: -0.1700

Data Index: 329050 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1066200 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2173. Min Act: -0.1700

Data Index: 737727 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2488. Min Act: -0.1700

Data Index: 759103 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2488. Min Act: -0.1700

Data Index: 1048296 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.1858. Min Act: -0.1700

Data Index: 157544 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.1858. Min Act: -0.1700

Data Index: 144303 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.1544. Min Act: -0.1700

Data Index: 568014 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.2802. Min Act: -0.1700

Data Index: 918234 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 3.5938. Min Range: -3.5938

Max Act: 3.1858. Min Act: -0.1700

Data Index: 738899 (C4 (Web Text))

Max Activating Token Index: 910