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

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

Neuron 471 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: 3.1396. Min Range: -3.1396

Max Act: 3.1267. Min Act: -0.1700

Data Index: 155448 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.1396. Min Act: -0.1700

Data Index: 662507 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.0982. Min Act: -0.1700

Data Index: 639157 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.1015. Min Act: -0.1700

Data Index: 366477 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.0390. Min Act: -0.1700

Data Index: 272218 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.0069. Min Act: -0.1700

Data Index: 777730 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.0107. Min Act: -0.1700

Data Index: 294789 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.1396. Min Range: -3.1396

Max Act: 3.0072. Min Act: -0.1700

Data Index: 847503 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9867. Min Act: -0.1700

Data Index: 1239308 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9965. Min Act: -0.1700

Data Index: 720921 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9900. Min Act: -0.1700

Data Index: 203603 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9970. Min Act: -0.1700

Data Index: 628841 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9924. Min Act: -0.1700

Data Index: 408963 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9713. Min Act: -0.1700

Data Index: 1468291 (Python Code)

Max Activating Token Index: 189

Text #14

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9770. Min Act: -0.1699

Data Index: 352578 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9735. Min Act: -0.1700

Data Index: 1121759 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9633. Min Act: -0.1700

Data Index: 521822 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9727. Min Act: -0.1698

Data Index: 1235317 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9712. Min Act: -0.1700

Data Index: 1330284 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.1396. Min Range: -3.1396

Max Act: 2.9664. Min Act: -0.1700

Data Index: 1031390 (C4 (Web Text))

Max Activating Token Index: 726