Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1077 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.9517. Min Act: -0.1700

Data Index: 366028 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.8453. Min Act: -0.1700

Data Index: 332356 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.7872. Min Act: -0.1700

Data Index: 1251441 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6877. Min Act: -0.1700

Data Index: 261390 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6244. Min Act: -0.1700

Data Index: 863189 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6117. Min Act: -0.1700

Data Index: 228261 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6300. Min Act: -0.1700

Data Index: 918083 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6499. Min Act: -0.1700

Data Index: 148827 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6100. Min Act: -0.1700

Data Index: 1227209 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6096. Min Act: -0.1700

Data Index: 641055 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6459. Min Act: -0.1700

Data Index: 909116 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6277. Min Act: -0.1700

Data Index: 1118763 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6329. Min Act: -0.1700

Data Index: 1125999 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5937. Min Act: -0.1700

Data Index: 629513 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6011. Min Act: -0.1700

Data Index: 840666 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.6066. Min Act: -0.1700

Data Index: 884833 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5801. Min Act: -0.1700

Data Index: 496705 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5994. Min Act: -0.1700

Data Index: 444735 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5942. Min Act: -0.1700

Data Index: 948651 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 3.9517. Min Range: -3.9517

Max Act: 3.5865. Min Act: -0.1700

Data Index: 328896 (C4 (Web Text))

Max Activating Token Index: 124