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

Dataset: Open Web Text

Neuron 1248 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: 2.7630. Min Range: -2.7630

Max Act: 2.7478. Min Act: -0.1700

Data Index: 7287262 (Open Web Text)

Max Activating Token Index: 691

Text #1

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7630. Min Act: -0.1700

Data Index: 5545249 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7629. Min Act: -0.1700

Data Index: 1205410 (Open Web Text)

Max Activating Token Index: 952

Text #3

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7309. Min Act: -0.1700

Data Index: 6330128 (Open Web Text)

Max Activating Token Index: 30

Text #4

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7202. Min Act: -0.1700

Data Index: 70314 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.7238. Min Act: -0.1700

Data Index: 1155249 (Open Web Text)

Max Activating Token Index: 413

Text #6

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6943. Min Act: -0.1700

Data Index: 3728180 (Open Web Text)

Max Activating Token Index: 988

Text #7

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6666. Min Act: -0.1700

Data Index: 8377376 (Open Web Text)

Max Activating Token Index: 507

Text #8

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6634. Min Act: -0.1700

Data Index: 102089 (Open Web Text)

Max Activating Token Index: 300

Text #9

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6658. Min Act: -0.1700

Data Index: 6362696 (Open Web Text)

Max Activating Token Index: 742

Text #10

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6462. Min Act: -0.1700

Data Index: 2220163 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6518. Min Act: -0.1700

Data Index: 3728181 (Open Web Text)

Max Activating Token Index: 57

Text #12

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6335. Min Act: -0.1700

Data Index: 5285271 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6360. Min Act: -0.1700

Data Index: 3777749 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6096. Min Act: -0.1700

Data Index: 1080616 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6134. Min Act: -0.1700

Data Index: 348493 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6115. Min Act: -0.1700

Data Index: 4091302 (Open Web Text)

Max Activating Token Index: 153

Text #17

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6024. Min Act: -0.1700

Data Index: 7388720 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6052. Min Act: -0.1700

Data Index: 7425121 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 2.7630. Min Range: -2.7630

Max Act: 2.6249. Min Act: -0.1700

Data Index: 6317492 (Open Web Text)

Max Activating Token Index: 855