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

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

Neuron 1575 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: 3.5542. Min Range: -3.5542

Max Act: 3.5275. Min Act: -0.1700

Data Index: 50277 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.5542. Min Act: -0.1700

Data Index: 1449824 (Python Code)

Max Activating Token Index: 171

Text #2

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3961. Min Act: -0.1700

Data Index: 835392 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.4002. Min Act: -0.1700

Data Index: 295842 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3805. Min Act: -0.1700

Data Index: 148127 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3664. Min Act: -0.1700

Data Index: 1129447 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3423. Min Act: -0.1700

Data Index: 848561 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3340. Min Act: -0.1700

Data Index: 1225611 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3419. Min Act: -0.1700

Data Index: 418468 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3227. Min Act: -0.1700

Data Index: 540671 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3198. Min Act: -0.1700

Data Index: 32094 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3054. Min Act: -0.1700

Data Index: 1093135 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2993. Min Act: -0.1700

Data Index: 965742 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.3134. Min Act: -0.1700

Data Index: 1066542 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2917. Min Act: -0.1700

Data Index: 312603 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2847. Min Act: -0.1700

Data Index: 1138030 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2814. Min Act: -0.1700

Data Index: 1307166 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2739. Min Act: -0.1700

Data Index: 332096 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2699. Min Act: -0.1700

Data Index: 426767 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 3.5542. Min Range: -3.5542

Max Act: 3.2545. Min Act: -0.1700

Data Index: 300426 (C4 (Web Text))

Max Activating Token Index: 388