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

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

Neuron 740 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: 3.6772. Min Range: -3.6772

Max Act: 3.6772. Min Act: -0.1700

Data Index: 94032 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.6189. Min Act: -0.1693

Data Index: 1342570 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.6233. Min Act: -0.1700

Data Index: 352030 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.5679. Min Act: -0.1700

Data Index: 424472 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.5702. Min Act: -0.1700

Data Index: 372558 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4762. Min Act: -0.1698

Data Index: 1212582 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4834. Min Act: -0.1700

Data Index: 623767 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4674. Min Act: -0.1700

Data Index: 201237 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4496. Min Act: -0.1700

Data Index: 654659 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4641. Min Act: -0.1700

Data Index: 231410 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4430. Min Act: -0.1699

Data Index: 456273 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4472. Min Act: -0.1700

Data Index: 884734 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4313. Min Act: -0.1700

Data Index: 1151841 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4338. Min Act: -0.1700

Data Index: 503305 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4268. Min Act: -0.1700

Data Index: 1100389 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4328. Min Act: -0.1700

Data Index: 574126 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4213. Min Act: -0.1700

Data Index: 668190 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4204. Min Act: -0.1700

Data Index: 725352 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4076. Min Act: -0.1700

Data Index: 154765 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 3.6772. Min Range: -3.6772

Max Act: 3.4264. Min Act: -0.1700

Data Index: 263475 (C4 (Web Text))

Max Activating Token Index: 376