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

Dataset: Open Web Text

Neuron 1671 in Layer 5

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: 3.3013. Min Range: -3.3013

Max Act: 3.3013. Min Act: -0.1700

Data Index: 5697505 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.2323. Min Act: -0.1700

Data Index: 8326252 (Open Web Text)

Max Activating Token Index: 419

Text #2

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1990. Min Act: -0.1700

Data Index: 1835056 (Open Web Text)

Max Activating Token Index: 731

Text #3

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1627. Min Act: -0.1700

Data Index: 5697504 (Open Web Text)

Max Activating Token Index: 239

Text #4

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1425. Min Act: -0.1700

Data Index: 8326249 (Open Web Text)

Max Activating Token Index: 333

Text #5

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1592. Min Act: -0.1700

Data Index: 3101457 (Open Web Text)

Max Activating Token Index: 215

Text #6

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1349. Min Act: -0.1700

Data Index: 5697499 (Open Web Text)

Max Activating Token Index: 870

Text #7

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1333. Min Act: -0.1700

Data Index: 4007800 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1143. Min Act: -0.1700

Data Index: 1626312 (Open Web Text)

Max Activating Token Index: 924

Text #9

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1225. Min Act: -0.1700

Data Index: 1374460 (Open Web Text)

Max Activating Token Index: 266

Text #10

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1227. Min Act: -0.1700

Data Index: 8361630 (Open Web Text)

Max Activating Token Index: 887

Text #11

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1205. Min Act: -0.1700

Data Index: 5899066 (Open Web Text)

Max Activating Token Index: 262

Text #12

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0939. Min Act: -0.1700

Data Index: 7043365 (Open Web Text)

Max Activating Token Index: 94

Text #13

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0915. Min Act: -0.1700

Data Index: 1835058 (Open Web Text)

Max Activating Token Index: 766

Text #14

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1080. Min Act: -0.1700

Data Index: 4674515 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.1181. Min Act: -0.1700

Data Index: 1783817 (Open Web Text)

Max Activating Token Index: 150

Text #16

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0698. Min Act: -0.1700

Data Index: 695960 (Open Web Text)

Max Activating Token Index: 875

Text #17

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0618. Min Act: -0.1700

Data Index: 2322396 (Open Web Text)

Max Activating Token Index: 57

Text #18

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0688. Min Act: -0.1700

Data Index: 5697501 (Open Web Text)

Max Activating Token Index: 226

Text #19

Max Range: 3.3013. Min Range: -3.3013

Max Act: 3.0725. Min Act: -0.1700

Data Index: 5697502 (Open Web Text)

Max Activating Token Index: 543