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

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

Neuron 1898 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: 3.4206. Min Range: -3.4206

Max Act: 3.4206. Min Act: -0.1700

Data Index: 1014451 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.4206. Min Act: -0.1700

Data Index: 1102685 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.3264. Min Act: -0.1700

Data Index: 1060464 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.3892. Min Act: -0.1700

Data Index: 367861 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.3264. Min Act: -0.1700

Data Index: 442040 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2950. Min Act: -0.1700

Data Index: 754323 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2950. Min Act: -0.1700

Data Index: 535966 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 40043 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 1278112 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 672926 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 120863 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2321. Min Act: -0.1700

Data Index: 561514 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.1692. Min Act: -0.1700

Data Index: 565194 (C4 (Web Text))

Max Activating Token Index: 1007

Text #13

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2321. Min Act: -0.1700

Data Index: 670284 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 261950 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2321. Min Act: -0.1700

Data Index: 232418 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1346186 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2636. Min Act: -0.1700

Data Index: 523238 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2321. Min Act: -0.1700

Data Index: 38184 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 3.4206. Min Range: -3.4206

Max Act: 3.2321. Min Act: -0.1700

Data Index: 1110784 (C4 (Web Text))

Max Activating Token Index: 756