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

Dataset: Open Web Text

Neuron 2393 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: 3.8509. Min Range: -3.8509

Max Act: 3.8509. Min Act: -0.1700

Data Index: 2622518 (Open Web Text)

Max Activating Token Index: 260

Text #1

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.7456. Min Act: -0.1700

Data Index: 6788332 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6924. Min Act: -0.1700

Data Index: 3915795 (Open Web Text)

Max Activating Token Index: 50

Text #3

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6061. Min Act: -0.1700

Data Index: 4702091 (Open Web Text)

Max Activating Token Index: 589

Text #4

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6760. Min Act: -0.1700

Data Index: 6416161 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6336. Min Act: -0.1700

Data Index: 3283132 (Open Web Text)

Max Activating Token Index: 666

Text #6

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6582. Min Act: -0.1700

Data Index: 5783725 (Open Web Text)

Max Activating Token Index: 384

Text #7

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6639. Min Act: -0.1700

Data Index: 4433926 (Open Web Text)

Max Activating Token Index: 51

Text #8

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6273. Min Act: -0.1700

Data Index: 7928572 (Open Web Text)

Max Activating Token Index: 512

Text #9

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6155. Min Act: -0.1700

Data Index: 5696174 (Open Web Text)

Max Activating Token Index: 124

Text #10

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6357. Min Act: -0.1700

Data Index: 5657897 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6253. Min Act: -0.1700

Data Index: 7968288 (Open Web Text)

Max Activating Token Index: 140

Text #12

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6233. Min Act: -0.1700

Data Index: 5143404 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.6081. Min Act: -0.1700

Data Index: 7885352 (Open Web Text)

Max Activating Token Index: 282

Text #14

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5932. Min Act: -0.1700

Data Index: 1580201 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5282. Min Act: -0.1700

Data Index: 7459250 (Open Web Text)

Max Activating Token Index: 779

Text #16

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5306. Min Act: -0.1700

Data Index: 7289258 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5310. Min Act: -0.1700

Data Index: 3904763 (Open Web Text)

Max Activating Token Index: 280

Text #18

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5496. Min Act: -0.1700

Data Index: 3867370 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.8509. Min Range: -3.8509

Max Act: 3.5479. Min Act: -0.1700

Data Index: 7046545 (Open Web Text)

Max Activating Token Index: 149