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

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

Neuron 891 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.2935. Min Act: -0.1700

Data Index: 179318 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.1685. Min Act: -0.1700

Data Index: 623292 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.1685. Min Act: -0.1700

Data Index: 126934 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0435. Min Act: -0.1700

Data Index: 673219 (C4 (Web Text))

Max Activating Token Index: 398

Text #4

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0435. Min Act: -0.1700

Data Index: 972890 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0435. Min Act: -0.1700

Data Index: 182819 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0747. Min Act: -0.1700

Data Index: 1030104 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0435. Min Act: -0.1700

Data Index: 533474 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 5.2935. Min Range: -5.2935

Max Act: 5.0122. Min Act: -0.1700

Data Index: 21682 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9810. Min Act: -0.1700

Data Index: 899572 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9810. Min Act: -0.1700

Data Index: 405420 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 674271 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 483640 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9810. Min Act: -0.1700

Data Index: 171846 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 215783 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 407916 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 69753 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.8872. Min Act: -0.1700

Data Index: 774280 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 915965 (C4 (Web Text))

Max Activating Token Index: 1001

Text #19

Max Range: 5.2935. Min Range: -5.2935

Max Act: 4.9497. Min Act: -0.1700

Data Index: 393263 (C4 (Web Text))

Max Activating Token Index: 548