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

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

Neuron 1993 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: 3.5243. Min Range: -3.5243

Max Act: 3.5243. Min Act: -0.1700

Data Index: 74555 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4581. Min Act: -0.1700

Data Index: 30121 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4628. Min Act: -0.1700

Data Index: 1182086 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4340. Min Act: -0.1700

Data Index: 926289 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4263. Min Act: -0.1700

Data Index: 560922 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3968. Min Act: -0.1700

Data Index: 761744 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4437. Min Act: -0.1700

Data Index: 595795 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4093. Min Act: -0.1700

Data Index: 1120283 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4012. Min Act: -0.1700

Data Index: 809613 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4006. Min Act: -0.1700

Data Index: 528869 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.4135. Min Act: -0.1700

Data Index: 961389 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3884. Min Act: -0.1700

Data Index: 91781 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3882. Min Act: -0.1700

Data Index: 34704 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3610. Min Act: -0.1700

Data Index: 592026 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3494. Min Act: -0.1700

Data Index: 1100763 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3291. Min Act: -0.1700

Data Index: 307034 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3250. Min Act: -0.1700

Data Index: 1044590 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3410. Min Act: -0.1700

Data Index: 922940 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3255. Min Act: -0.1700

Data Index: 231794 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 3.5243. Min Range: -3.5243

Max Act: 3.3394. Min Act: -0.1700

Data Index: 163974 (C4 (Web Text))

Max Activating Token Index: 296