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

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

Neuron 1264 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: 3.9742. Min Range: -3.9742

Max Act: 3.9742. Min Act: -0.1700

Data Index: 48403 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.7273. Min Act: -0.1700

Data Index: 354658 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6710. Min Act: -0.1700

Data Index: 1056486 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6848. Min Act: -0.1700

Data Index: 662453 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6679. Min Act: -0.1700

Data Index: 1219912 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6343. Min Act: -0.1700

Data Index: 884899 (C4 (Web Text))

Max Activating Token Index: 998

Text #6

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6315. Min Act: -0.1700

Data Index: 1076083 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6300. Min Act: -0.1700

Data Index: 25759 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1142304 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5839. Min Act: -0.1700

Data Index: 335676 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.6060. Min Act: -0.1700

Data Index: 1027617 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5988. Min Act: -0.1700

Data Index: 290550 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1269635 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5779. Min Act: -0.1700

Data Index: 1241001 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5839. Min Act: -0.1700

Data Index: 1085424 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5513. Min Act: -0.1700

Data Index: 1065484 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5545. Min Act: -0.1700

Data Index: 1048229 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5574. Min Act: -0.1700

Data Index: 428590 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5134. Min Act: -0.1700

Data Index: 639036 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.5311. Min Act: -0.1700

Data Index: 628231 (C4 (Web Text))

Max Activating Token Index: 952