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

Dataset: Open Web Text

Neuron 2267 in Layer 4

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: 3.8297. Min Range: -3.8297

Max Act: 3.8297. Min Act: -0.1700

Data Index: 3487059 (Open Web Text)

Max Activating Token Index: 627

Text #1

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.7805. Min Act: -0.1700

Data Index: 1093807 (Open Web Text)

Max Activating Token Index: 289

Text #2

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6693. Min Act: -0.1700

Data Index: 3037991 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6710. Min Act: -0.1700

Data Index: 3716343 (Open Web Text)

Max Activating Token Index: 931

Text #4

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6571. Min Act: -0.1700

Data Index: 5828798 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6193. Min Act: -0.1700

Data Index: 7544305 (Open Web Text)

Max Activating Token Index: 557

Text #6

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.6240. Min Act: -0.1700

Data Index: 5184236 (Open Web Text)

Max Activating Token Index: 577

Text #7

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5698. Min Act: -0.1700

Data Index: 29722 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5655. Min Act: -0.1700

Data Index: 4922687 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5626. Min Act: -0.1700

Data Index: 1846142 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5877. Min Act: -0.1700

Data Index: 6867827 (Open Web Text)

Max Activating Token Index: 542

Text #11

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5469. Min Act: -0.1700

Data Index: 6304437 (Open Web Text)

Max Activating Token Index: 739

Text #12

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.4797. Min Act: -0.1700

Data Index: 5235700 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5318. Min Act: -0.1700

Data Index: 8793104 (Open Web Text)

Max Activating Token Index: 252

Text #14

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5533. Min Act: -0.1700

Data Index: 8024319 (Open Web Text)

Max Activating Token Index: 418

Text #15

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5271. Min Act: -0.1700

Data Index: 1031780 (Open Web Text)

Max Activating Token Index: 646

Text #16

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5330. Min Act: -0.1700

Data Index: 5226475 (Open Web Text)

Max Activating Token Index: 696

Text #17

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5091. Min Act: -0.1700

Data Index: 6094469 (Open Web Text)

Max Activating Token Index: 187

Text #18

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.5105. Min Act: -0.1700

Data Index: 4148051 (Open Web Text)

Max Activating Token Index: 360

Text #19

Max Range: 3.8297. Min Range: -3.8297

Max Act: 3.4595. Min Act: -0.1700

Data Index: 5205345 (Open Web Text)

Max Activating Token Index: 658