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

Dataset: Open Web Text

Neuron 1705 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: 1.8599. Min Range: -1.8599

Max Act: 1.8599. Min Act: -0.1700

Data Index: 36707 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7288. Min Act: -0.1700

Data Index: 2407256 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7375. Min Act: -0.1700

Data Index: 3665406 (Open Web Text)

Max Activating Token Index: 387

Text #3

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7217. Min Act: -0.1700

Data Index: 2477278 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.7082. Min Act: -0.1700

Data Index: 3079737 (Open Web Text)

Max Activating Token Index: 508

Text #5

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6778. Min Act: -0.1700

Data Index: 3044825 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6674. Min Act: -0.1700

Data Index: 3969983 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6546. Min Act: -0.1700

Data Index: 6423640 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6520. Min Act: -0.1700

Data Index: 218213 (Open Web Text)

Max Activating Token Index: 148

Text #9

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6717. Min Act: -0.1700

Data Index: 4808919 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6535. Min Act: -0.1700

Data Index: 4559556 (Open Web Text)

Max Activating Token Index: 120

Text #11

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6577. Min Act: -0.1700

Data Index: 5163645 (Open Web Text)

Max Activating Token Index: 35

Text #12

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6578. Min Act: -0.1700

Data Index: 1959531 (Open Web Text)

Max Activating Token Index: 586

Text #13

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6540. Min Act: -0.1700

Data Index: 5228246 (Open Web Text)

Max Activating Token Index: 788

Text #14

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6554. Min Act: -0.1700

Data Index: 7531380 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6445. Min Act: -0.1700

Data Index: 1745516 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6395. Min Act: -0.1700

Data Index: 1060103 (Open Web Text)

Max Activating Token Index: 269

Text #17

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6372. Min Act: -0.1700

Data Index: 2978117 (Open Web Text)

Max Activating Token Index: 676

Text #18

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6345. Min Act: -0.1700

Data Index: 900197 (Open Web Text)

Max Activating Token Index: 472

Text #19

Max Range: 1.8599. Min Range: -1.8599

Max Act: 1.6397. Min Act: -0.1700

Data Index: 7465520 (Open Web Text)

Max Activating Token Index: 591