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

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

Neuron 433 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: 3.4843. Min Range: -3.4843

Max Act: 3.4843. Min Act: -0.1700

Data Index: 971984 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.3588. Min Act: -0.1700

Data Index: 660779 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.2803. Min Act: -0.1700

Data Index: 1105138 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.2803. Min Act: -0.1700

Data Index: 840897 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.2803. Min Act: -0.1700

Data Index: 1246655 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.2175. Min Act: -0.1700

Data Index: 296280 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.2175. Min Act: -0.1700

Data Index: 233884 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1703. Min Act: -0.1700

Data Index: 478816 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1703. Min Act: -0.1700

Data Index: 255432 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1545. Min Act: -0.1700

Data Index: 42756 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1230. Min Act: -0.1700

Data Index: 757156 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1388. Min Act: -0.1700

Data Index: 232297 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1230. Min Act: -0.1700

Data Index: 1089688 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1072. Min Act: -0.1700

Data Index: 11890 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.0915. Min Act: -0.1700

Data Index: 1281001 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.0915. Min Act: -0.1700

Data Index: 34159 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.0757. Min Act: -0.1700

Data Index: 1278398 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.0757. Min Act: -0.1700

Data Index: 281443 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.0757. Min Act: -0.1700

Data Index: 185035 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 3.4843. Min Range: -3.4843

Max Act: 3.1230. Min Act: -0.1700

Data Index: 57484 (C4 (Web Text))

Max Activating Token Index: 424