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

Dataset: Open Web Text

Neuron 139 in Layer 1

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: 1.9192. Min Range: -1.9192

Max Act: 1.9192. Min Act: -0.1700

Data Index: 226987 (Open Web Text)

Max Activating Token Index: 1012

Text #1

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.9004. Min Act: -0.1700

Data Index: 189691 (Open Web Text)

Max Activating Token Index: 872

Text #2

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8922. Min Act: -0.1700

Data Index: 7649850 (Open Web Text)

Max Activating Token Index: 54

Text #3

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8572. Min Act: -0.1700

Data Index: 226988 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8541. Min Act: -0.1700

Data Index: 7649849 (Open Web Text)

Max Activating Token Index: 484

Text #5

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8314. Min Act: -0.1700

Data Index: 5137970 (Open Web Text)

Max Activating Token Index: 406

Text #6

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8312. Min Act: -0.1654

Data Index: 6146017 (Open Web Text)

Max Activating Token Index: 334

Text #7

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8303. Min Act: -0.1700

Data Index: 4384257 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8185. Min Act: -0.1687

Data Index: 60204 (Open Web Text)

Max Activating Token Index: 67

Text #9

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8146. Min Act: -0.1623

Data Index: 5517101 (Open Web Text)

Max Activating Token Index: 378

Text #10

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8251. Min Act: -0.1687

Data Index: 5314701 (Open Web Text)

Max Activating Token Index: 729

Text #11

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8168. Min Act: -0.1662

Data Index: 7615583 (Open Web Text)

Max Activating Token Index: 360

Text #12

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8200. Min Act: -0.1690

Data Index: 886979 (Open Web Text)

Max Activating Token Index: 217

Text #13

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8147. Min Act: -0.1700

Data Index: 189692 (Open Web Text)

Max Activating Token Index: 442

Text #14

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8127. Min Act: -0.1685

Data Index: 5678449 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8070. Min Act: -0.1700

Data Index: 2423449 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8092. Min Act: -0.1700

Data Index: 1698030 (Open Web Text)

Max Activating Token Index: 285

Text #17

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8145. Min Act: -0.1700

Data Index: 1698031 (Open Web Text)

Max Activating Token Index: 506

Text #18

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8082. Min Act: -0.1678

Data Index: 7058762 (Open Web Text)

Max Activating Token Index: 351

Text #19

Max Range: 1.9192. Min Range: -1.9192

Max Act: 1.8019. Min Act: -0.1700

Data Index: 5486232 (Open Web Text)

Max Activating Token Index: 182