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

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

Neuron 1196 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: 4.1000. Min Range: -4.1000

Max Act: 4.1000. Min Act: -0.1700

Data Index: 653504 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0528. Min Act: -0.1700

Data Index: 520214 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0547. Min Act: -0.1700

Data Index: 93620 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0316. Min Act: -0.1700

Data Index: 200257 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0466. Min Act: -0.1700

Data Index: 88359 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0612. Min Act: -0.1700

Data Index: 916265 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0341. Min Act: -0.1700

Data Index: 92946 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 4.1000. Min Range: -4.1000

Max Act: 4.0434. Min Act: -0.1700

Data Index: 667273 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9886. Min Act: -0.1700

Data Index: 1278495 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9717. Min Act: -0.1700

Data Index: 1316225 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9300. Min Act: -0.1700

Data Index: 922394 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9403. Min Act: -0.1700

Data Index: 60270 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9573. Min Act: -0.1700

Data Index: 445246 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9043. Min Act: -0.1700

Data Index: 395612 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9041. Min Act: -0.1700

Data Index: 712237 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.9198. Min Act: -0.1700

Data Index: 765445 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.8942. Min Act: -0.1700

Data Index: 247558 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.8637. Min Act: -0.1700

Data Index: 1115513 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.8616. Min Act: -0.1700

Data Index: 900659 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 4.1000. Min Range: -4.1000

Max Act: 3.7713. Min Act: -0.1700

Data Index: 846310 (C4 (Web Text))

Max Activating Token Index: 876