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

Dataset: Open Web Text

Neuron 2500 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: 6.9984. Min Range: -6.9984

Max Act: 6.9984. Min Act: -0.1700

Data Index: 3271054 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.9502. Min Act: -0.1700

Data Index: 1359228 (Open Web Text)

Max Activating Token Index: 75

Text #2

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.9551. Min Act: -0.1700

Data Index: 4369932 (Open Web Text)

Max Activating Token Index: 288

Text #3

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.9060. Min Act: -0.1700

Data Index: 1258079 (Open Web Text)

Max Activating Token Index: 156

Text #4

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8702. Min Act: -0.1700

Data Index: 550181 (Open Web Text)

Max Activating Token Index: 680

Text #5

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8773. Min Act: -0.1700

Data Index: 4877752 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8749. Min Act: -0.1700

Data Index: 7716706 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8622. Min Act: -0.1700

Data Index: 1038154 (Open Web Text)

Max Activating Token Index: 27

Text #8

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8565. Min Act: -0.1700

Data Index: 5400581 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8738. Min Act: -0.1700

Data Index: 537494 (Open Web Text)

Max Activating Token Index: 452

Text #10

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8546. Min Act: -0.1700

Data Index: 5545740 (Open Web Text)

Max Activating Token Index: 43

Text #11

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8225. Min Act: -0.1700

Data Index: 8618259 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8101. Min Act: -0.1700

Data Index: 7882306 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8252. Min Act: -0.1700

Data Index: 367950 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8167. Min Act: -0.1700

Data Index: 6154333 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8285. Min Act: -0.1700

Data Index: 1308203 (Open Web Text)

Max Activating Token Index: 192

Text #16

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8190. Min Act: -0.1700

Data Index: 5648925 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.8160. Min Act: -0.1700

Data Index: 1121051 (Open Web Text)

Max Activating Token Index: 301

Text #18

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.7977. Min Act: -0.1700

Data Index: 4877739 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 6.9984. Min Range: -6.9984

Max Act: 6.7919. Min Act: -0.1700

Data Index: 550183 (Open Web Text)

Max Activating Token Index: 293