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

Dataset: Open Web Text

Neuron 2307 in Layer 0

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: 4.5847. Min Range: -4.5847

Max Act: 4.5847. Min Act: -0.1700

Data Index: 1662333 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.4348. Min Act: -0.1698

Data Index: 6774926 (Open Web Text)

Max Activating Token Index: 378

Text #2

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.4501. Min Act: -0.1493

Data Index: 149749 (Open Web Text)

Max Activating Token Index: 182

Text #3

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.4303. Min Act: -0.1599

Data Index: 6774913 (Open Web Text)

Max Activating Token Index: 447

Text #4

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.4009. Min Act: -0.1154

Data Index: 8755386 (Open Web Text)

Max Activating Token Index: 428

Text #5

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.4069. Min Act: -0.1599

Data Index: 6774923 (Open Web Text)

Max Activating Token Index: 401

Text #6

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3763. Min Act: -0.1523

Data Index: 8818915 (Open Web Text)

Max Activating Token Index: 961

Text #7

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3914. Min Act: -0.1578

Data Index: 8818916 (Open Web Text)

Max Activating Token Index: 348

Text #8

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3872. Min Act: -0.1340

Data Index: 8818911 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3900. Min Act: -0.1486

Data Index: 6774916 (Open Web Text)

Max Activating Token Index: 424

Text #10

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3888. Min Act: -0.1529

Data Index: 6563217 (Open Web Text)

Max Activating Token Index: 260

Text #11

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3798. Min Act: -0.1683

Data Index: 8818933 (Open Web Text)

Max Activating Token Index: 680

Text #12

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3764. Min Act: -0.1439

Data Index: 8818920 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3426. Min Act: -0.1613

Data Index: 8818935 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3623. Min Act: -0.1498

Data Index: 2589982 (Open Web Text)

Max Activating Token Index: 539

Text #15

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3629. Min Act: -0.1563

Data Index: 8818931 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3405. Min Act: -0.1700

Data Index: 1494739 (Open Web Text)

Max Activating Token Index: 674

Text #17

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3527. Min Act: -0.1008

Data Index: 2608425 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3428. Min Act: -0.1467

Data Index: 2608421 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 4.5847. Min Range: -4.5847

Max Act: 4.3141. Min Act: -0.1468

Data Index: 8818910 (Open Web Text)

Max Activating Token Index: 464