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

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

Neuron 1471 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: 3.6905. Min Range: -3.6905

Max Act: 3.6905. Min Act: -0.1700

Data Index: 1523550 (Python Code)

Max Activating Token Index: 435

Text #1

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5987. Min Act: -0.1700

Data Index: 506698 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5555. Min Act: -0.1700

Data Index: 1465311 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5411. Min Act: -0.1700

Data Index: 1267735 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5230. Min Act: -0.1700

Data Index: 1452953 (Python Code)

Max Activating Token Index: 435

Text #5

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5115. Min Act: -0.1700

Data Index: 1560275 (Python Code)

Max Activating Token Index: 541

Text #6

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5292. Min Act: -0.1700

Data Index: 81117 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.5205. Min Act: -0.1700

Data Index: 978395 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4917. Min Act: -0.1700

Data Index: 214882 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4932. Min Act: -0.1700

Data Index: 324134 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4635. Min Act: -0.1700

Data Index: 1561636 (Python Code)

Max Activating Token Index: 564

Text #11

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4866. Min Act: -0.1700

Data Index: 441653 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4766. Min Act: -0.1700

Data Index: 1394383 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4746. Min Act: -0.1700

Data Index: 390884 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4693. Min Act: -0.1700

Data Index: 57297 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4689. Min Act: -0.1700

Data Index: 106731 (C4 (Web Text))

Max Activating Token Index: 790

Text #16

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4383. Min Act: -0.1700

Data Index: 1302548 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4629. Min Act: -0.1700

Data Index: 521159 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4466. Min Act: -0.1700

Data Index: 557098 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.6905. Min Range: -3.6905

Max Act: 3.4416. Min Act: -0.1700

Data Index: 1559354 (Python Code)

Max Activating Token Index: 179