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

Dataset: Open Web Text

Neuron 1026 in Layer 1

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: 5.1294. Min Range: -5.1294

Max Act: 5.1189. Min Act: -0.1700

Data Index: 3975979 (Open Web Text)

Max Activating Token Index: 698

Text #1

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.1294. Min Act: -0.1700

Data Index: 5811453 (Open Web Text)

Max Activating Token Index: 401

Text #2

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0739. Min Act: -0.1700

Data Index: 6146580 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0598. Min Act: -0.1700

Data Index: 462298 (Open Web Text)

Max Activating Token Index: 357

Text #4

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0787. Min Act: -0.1700

Data Index: 3536110 (Open Web Text)

Max Activating Token Index: 496

Text #5

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0529. Min Act: -0.1700

Data Index: 2712881 (Open Web Text)

Max Activating Token Index: 834

Text #6

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0637. Min Act: -0.1700

Data Index: 5893680 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0501. Min Act: -0.1700

Data Index: 2089523 (Open Web Text)

Max Activating Token Index: 604

Text #8

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0425. Min Act: -0.1700

Data Index: 5672519 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0145. Min Act: -0.1700

Data Index: 2083242 (Open Web Text)

Max Activating Token Index: 741

Text #10

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0206. Min Act: -0.1700

Data Index: 755983 (Open Web Text)

Max Activating Token Index: 726

Text #11

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0343. Min Act: -0.1699

Data Index: 131294 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0386. Min Act: -0.1699

Data Index: 7655135 (Open Web Text)

Max Activating Token Index: 358

Text #13

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0195. Min Act: -0.1700

Data Index: 2893977 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0405. Min Act: -0.1700

Data Index: 3439576 (Open Web Text)

Max Activating Token Index: 402

Text #15

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0502. Min Act: -0.1700

Data Index: 5296160 (Open Web Text)

Max Activating Token Index: 215

Text #16

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0424. Min Act: -0.1700

Data Index: 3215287 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 5.1294. Min Range: -5.1294

Max Act: 4.9954. Min Act: -0.1700

Data Index: 3294586 (Open Web Text)

Max Activating Token Index: 235

Text #18

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0130. Min Act: -0.1700

Data Index: 3472818 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 5.1294. Min Range: -5.1294

Max Act: 5.0184. Min Act: -0.1700

Data Index: 1519009 (Open Web Text)

Max Activating Token Index: 266