Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 353 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.6437. Min Act: -0.1700

Data Index: 5761929 (Open Web Text)

Max Activating Token Index: 368

Text #1

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.6137. Min Act: -0.1700

Data Index: 30623 (Open Web Text)

Max Activating Token Index: 689

Text #2

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5423. Min Act: -0.1700

Data Index: 5577704 (Open Web Text)

Max Activating Token Index: 440

Text #3

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5551. Min Act: -0.1700

Data Index: 5850798 (Open Web Text)

Max Activating Token Index: 433

Text #4

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5110. Min Act: -0.1700

Data Index: 2513226 (Open Web Text)

Max Activating Token Index: 186

Text #5

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5254. Min Act: -0.1700

Data Index: 3279770 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4880. Min Act: -0.1700

Data Index: 3984620 (Open Web Text)

Max Activating Token Index: 877

Text #7

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4931. Min Act: -0.1700

Data Index: 5383228 (Open Web Text)

Max Activating Token Index: 289

Text #8

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4990. Min Act: -0.1700

Data Index: 7579994 (Open Web Text)

Max Activating Token Index: 874

Text #9

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4533. Min Act: -0.1700

Data Index: 5345672 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4651. Min Act: -0.1700

Data Index: 7744300 (Open Web Text)

Max Activating Token Index: 915

Text #11

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4785. Min Act: -0.1700

Data Index: 443727 (Open Web Text)

Max Activating Token Index: 187

Text #12

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4699. Min Act: -0.1700

Data Index: 2602189 (Open Web Text)

Max Activating Token Index: 142

Text #13

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.5045. Min Act: -0.1700

Data Index: 6437060 (Open Web Text)

Max Activating Token Index: 593

Text #14

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4988. Min Act: -0.1700

Data Index: 3904713 (Open Web Text)

Max Activating Token Index: 522

Text #15

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4458. Min Act: -0.1700

Data Index: 2056643 (Open Web Text)

Max Activating Token Index: 1018

Text #16

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4779. Min Act: -0.1700

Data Index: 5839271 (Open Web Text)

Max Activating Token Index: 770

Text #17

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4512. Min Act: -0.1700

Data Index: 1279671 (Open Web Text)

Max Activating Token Index: 386

Text #18

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4381. Min Act: -0.1700

Data Index: 5868206 (Open Web Text)

Max Activating Token Index: 410

Text #19

Max Range: 3.6437. Min Range: -3.6437

Max Act: 3.4642. Min Act: -0.1700

Data Index: 7109550 (Open Web Text)

Max Activating Token Index: 464