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

Dataset: Open Web Text

Neuron 638 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: 3.2422. Min Range: -3.2422

Max Act: 3.2422. Min Act: -0.1700

Data Index: 6608145 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.2085. Min Act: -0.1700

Data Index: 5039309 (Open Web Text)

Max Activating Token Index: 628

Text #2

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.2005. Min Act: -0.1700

Data Index: 1736633 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1732. Min Act: -0.1700

Data Index: 7302671 (Open Web Text)

Max Activating Token Index: 242

Text #4

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1657. Min Act: -0.1700

Data Index: 755736 (Open Web Text)

Max Activating Token Index: 122

Text #5

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1557. Min Act: -0.1700

Data Index: 403400 (Open Web Text)

Max Activating Token Index: 84

Text #6

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1359. Min Act: -0.1700

Data Index: 1912021 (Open Web Text)

Max Activating Token Index: 589

Text #7

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1237. Min Act: -0.1700

Data Index: 2465264 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1117. Min Act: -0.1700

Data Index: 5975267 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1141. Min Act: -0.1700

Data Index: 7678181 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1146. Min Act: -0.1700

Data Index: 4667454 (Open Web Text)

Max Activating Token Index: 149

Text #11

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.1022. Min Act: -0.1700

Data Index: 3970409 (Open Web Text)

Max Activating Token Index: 681

Text #12

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0796. Min Act: -0.1700

Data Index: 8807412 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0750. Min Act: -0.1700

Data Index: 2753397 (Open Web Text)

Max Activating Token Index: 208

Text #14

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0965. Min Act: -0.1700

Data Index: 378592 (Open Web Text)

Max Activating Token Index: 26

Text #15

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0725. Min Act: -0.1700

Data Index: 5927705 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0632. Min Act: -0.1700

Data Index: 6621902 (Open Web Text)

Max Activating Token Index: 320

Text #17

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0705. Min Act: -0.1700

Data Index: 3127091 (Open Web Text)

Max Activating Token Index: 463

Text #18

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0625. Min Act: -0.1700

Data Index: 197101 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 3.2422. Min Range: -3.2422

Max Act: 3.0633. Min Act: -0.1700

Data Index: 133424 (Open Web Text)

Max Activating Token Index: 139