Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 192 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4955. Min Act: -0.1700

Data Index: 58522 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4328. Min Act: -0.1700

Data Index: 1122109 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1261228 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4014. Min Act: -0.1700

Data Index: 1316625 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4171. Min Act: -0.1700

Data Index: 189515 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3543. Min Act: -0.1700

Data Index: 944102 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4014. Min Act: -0.1700

Data Index: 1281640 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3857. Min Act: -0.1700

Data Index: 392093 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.4014. Min Act: -0.1700

Data Index: 714375 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3543. Min Act: -0.1700

Data Index: 236400 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3229. Min Act: -0.1700

Data Index: 398017 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3543. Min Act: -0.1700

Data Index: 945399 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3700. Min Act: -0.1700

Data Index: 41926 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.3386. Min Act: -0.1700

Data Index: 123176 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2915. Min Act: -0.1700

Data Index: 982655 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2758. Min Act: -0.1700

Data Index: 574099 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2758. Min Act: -0.1700

Data Index: 260476 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2601. Min Act: -0.1700

Data Index: 722266 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1045608 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 3.4955. Min Range: -3.4955

Max Act: 3.2915. Min Act: -0.1700

Data Index: 1121863 (C4 (Web Text))

Max Activating Token Index: 585