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

Dataset: Open Web Text

Neuron 2356 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: 3.7145. Min Range: -3.7145

Max Act: 3.7145. Min Act: -0.1700

Data Index: 8396430 (Open Web Text)

Max Activating Token Index: 1019

Text #1

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.6237. Min Act: -0.1700

Data Index: 5917309 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.6052. Min Act: -0.1700

Data Index: 332241 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5761. Min Act: -0.1700

Data Index: 8132666 (Open Web Text)

Max Activating Token Index: 143

Text #4

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5571. Min Act: -0.1700

Data Index: 8096058 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5614. Min Act: -0.1700

Data Index: 2658651 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5647. Min Act: -0.1700

Data Index: 879262 (Open Web Text)

Max Activating Token Index: 197

Text #7

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5678. Min Act: -0.1700

Data Index: 5855242 (Open Web Text)

Max Activating Token Index: 766

Text #8

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5574. Min Act: -0.1700

Data Index: 6049003 (Open Web Text)

Max Activating Token Index: 335

Text #9

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1131529 (Open Web Text)

Max Activating Token Index: 759

Text #10

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5451. Min Act: -0.1700

Data Index: 5601615 (Open Web Text)

Max Activating Token Index: 264

Text #11

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5498. Min Act: -0.1700

Data Index: 1103302 (Open Web Text)

Max Activating Token Index: 1002

Text #12

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5331. Min Act: -0.1700

Data Index: 6441612 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5352. Min Act: -0.1700

Data Index: 3158717 (Open Web Text)

Max Activating Token Index: 660

Text #14

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5257. Min Act: -0.1700

Data Index: 5202630 (Open Web Text)

Max Activating Token Index: 147

Text #15

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5091. Min Act: -0.1700

Data Index: 4454420 (Open Web Text)

Max Activating Token Index: 589

Text #16

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5203. Min Act: -0.1700

Data Index: 1218031 (Open Web Text)

Max Activating Token Index: 427

Text #17

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.5039. Min Act: -0.1700

Data Index: 6563816 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.4855. Min Act: -0.1700

Data Index: 2483755 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 3.7145. Min Range: -3.7145

Max Act: 3.4709. Min Act: -0.1700

Data Index: 3188192 (Open Web Text)

Max Activating Token Index: 149