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

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

Neuron 203 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: 4.0820. Min Range: -4.0820

Max Act: 4.0820. Min Act: -0.1699

Data Index: 66987 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 4.0820. Min Range: -4.0820

Max Act: 4.0508. Min Act: -0.1700

Data Index: 141239 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 4.0820. Min Range: -4.0820

Max Act: 4.0195. Min Act: -0.1700

Data Index: 229226 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9883. Min Act: -0.1700

Data Index: 490189 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 4.0820. Min Range: -4.0820

Max Act: 4.0508. Min Act: -0.1700

Data Index: 101074 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9883. Min Act: -0.1700

Data Index: 380736 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9883. Min Act: -0.1700

Data Index: 1261358 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9883. Min Act: -0.1700

Data Index: 962818 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.8944. Min Act: -0.1700

Data Index: 563196 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1289667 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 1319576 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 305057 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9570. Min Act: -0.1700

Data Index: 451002 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 564248 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9570. Min Act: -0.1700

Data Index: 716246 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9570. Min Act: -0.1700

Data Index: 234235 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 35036 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 471745 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 920124 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 4.0820. Min Range: -4.0820

Max Act: 3.9257. Min Act: -0.1700

Data Index: 531058 (C4 (Web Text))

Max Activating Token Index: 51