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

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

Neuron 440 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: 3.4782. Min Range: -3.4782

Max Act: 3.4767. Min Act: -0.1700

Data Index: 258991 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.4748. Min Act: -0.1700

Data Index: 228600 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1415914 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.4604. Min Act: -0.1700

Data Index: 1376993 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.4782. Min Act: -0.1700

Data Index: 630931 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.4528. Min Act: -0.1700

Data Index: 1482290 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3586. Min Act: -0.1700

Data Index: 466711 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3639. Min Act: -0.1700

Data Index: 524810 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3542. Min Act: -0.1700

Data Index: 360702 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3334. Min Act: -0.1700

Data Index: 621630 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3436. Min Act: -0.1700

Data Index: 196732 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3369. Min Act: -0.1700

Data Index: 725982 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3288. Min Act: -0.1700

Data Index: 234328 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3112. Min Act: -0.1700

Data Index: 1382567 (Python Code)

Max Activating Token Index: 686

Text #14

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3210. Min Act: -0.1700

Data Index: 1182648 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3065. Min Act: -0.1700

Data Index: 315224 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3046. Min Act: -0.1700

Data Index: 73843 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2979. Min Act: -0.1700

Data Index: 827227 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3013. Min Act: -0.1700

Data Index: 1223660 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2748. Min Act: -0.1700

Data Index: 1094670 (C4 (Web Text))

Max Activating Token Index: 574