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

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

Neuron 525 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: 3.0596. Min Range: -3.0596

Max Act: 3.0596. Min Act: -0.1700

Data Index: 727331 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9900. Min Act: -0.1700

Data Index: 1655002 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9749. Min Act: -0.1700

Data Index: 329082 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9577. Min Act: -0.1700

Data Index: 70641 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9668. Min Act: -0.1700

Data Index: 44208 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9703. Min Act: -0.1700

Data Index: 863997 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9489. Min Act: -0.1700

Data Index: 437416 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9410. Min Act: -0.1700

Data Index: 437914 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9500. Min Act: -0.1700

Data Index: 231546 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9082. Min Act: -0.1700

Data Index: 1354340 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9350. Min Act: -0.1700

Data Index: 94397 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9333. Min Act: -0.1700

Data Index: 1320896 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9180. Min Act: -0.1700

Data Index: 1506954 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9132. Min Act: -0.1700

Data Index: 1422411 (Python Code)

Max Activating Token Index: 735

Text #14

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9181. Min Act: -0.1700

Data Index: 1625547 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9158. Min Act: -0.1700

Data Index: 528568 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9028. Min Act: -0.1700

Data Index: 325025 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9193. Min Act: -0.1700

Data Index: 843237 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9116. Min Act: -0.1700

Data Index: 488719 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 3.0596. Min Range: -3.0596

Max Act: 2.9340. Min Act: -0.1700

Data Index: 227272 (C4 (Web Text))

Max Activating Token Index: 753