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

Dataset: Open Web Text

Neuron 559 in Layer 3

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: 3.8661. Min Range: -3.8661

Max Act: 3.8661. Min Act: -0.1700

Data Index: 6655784 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8186. Min Act: -0.1700

Data Index: 6695812 (Open Web Text)

Max Activating Token Index: 145

Text #2

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8045. Min Act: -0.1700

Data Index: 4996715 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.8053. Min Act: -0.1700

Data Index: 3285380 (Open Web Text)

Max Activating Token Index: 974

Text #4

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7606. Min Act: -0.1700

Data Index: 5154761 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7578. Min Act: -0.1700

Data Index: 6948526 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7211. Min Act: -0.1700

Data Index: 5442228 (Open Web Text)

Max Activating Token Index: 466

Text #7

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7313. Min Act: -0.1700

Data Index: 2463403 (Open Web Text)

Max Activating Token Index: 686

Text #8

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7253. Min Act: -0.1700

Data Index: 6550306 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7114. Min Act: -0.1700

Data Index: 4984312 (Open Web Text)

Max Activating Token Index: 526

Text #10

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7109. Min Act: -0.1700

Data Index: 6330793 (Open Web Text)

Max Activating Token Index: 319

Text #11

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7380. Min Act: -0.1700

Data Index: 1632782 (Open Web Text)

Max Activating Token Index: 657

Text #12

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6835. Min Act: -0.1700

Data Index: 5689545 (Open Web Text)

Max Activating Token Index: 398

Text #13

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6917. Min Act: -0.1700

Data Index: 1181337 (Open Web Text)

Max Activating Token Index: 155

Text #14

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6882. Min Act: -0.1700

Data Index: 2786327 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7008. Min Act: -0.1700

Data Index: 8498755 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7165. Min Act: -0.1700

Data Index: 8445490 (Open Web Text)

Max Activating Token Index: 652

Text #17

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7056. Min Act: -0.1700

Data Index: 713509 (Open Web Text)

Max Activating Token Index: 330

Text #18

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.6975. Min Act: -0.1700

Data Index: 6908717 (Open Web Text)

Max Activating Token Index: 448

Text #19

Max Range: 3.8661. Min Range: -3.8661

Max Act: 3.7313. Min Act: -0.1700

Data Index: 8537574 (Open Web Text)

Max Activating Token Index: 865