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

Dataset: Open Web Text

Neuron 1568 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: 1.9127. Min Range: -1.9127

Max Act: 1.9127. Min Act: -0.1700

Data Index: 5972926 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.9026. Min Act: -0.1700

Data Index: 5526796 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8874. Min Act: -0.1700

Data Index: 2304128 (Open Web Text)

Max Activating Token Index: 963

Text #3

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8743. Min Act: -0.1698

Data Index: 2304132 (Open Web Text)

Max Activating Token Index: 647

Text #4

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8839. Min Act: -0.1700

Data Index: 2218878 (Open Web Text)

Max Activating Token Index: 657

Text #5

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8509. Min Act: -0.1700

Data Index: 1570034 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8367. Min Act: -0.1700

Data Index: 3168605 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8477. Min Act: -0.1700

Data Index: 6280828 (Open Web Text)

Max Activating Token Index: 330

Text #8

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8366. Min Act: -0.1700

Data Index: 57684 (Open Web Text)

Max Activating Token Index: 112

Text #9

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8374. Min Act: -0.1700

Data Index: 2129231 (Open Web Text)

Max Activating Token Index: 969

Text #10

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8229. Min Act: -0.1700

Data Index: 2304131 (Open Web Text)

Max Activating Token Index: 573

Text #11

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8356. Min Act: -0.1700

Data Index: 2981576 (Open Web Text)

Max Activating Token Index: 641

Text #12

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8312. Min Act: -0.1700

Data Index: 4223930 (Open Web Text)

Max Activating Token Index: 350

Text #13

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8300. Min Act: -0.1700

Data Index: 4621205 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8279. Min Act: -0.1700

Data Index: 2129220 (Open Web Text)

Max Activating Token Index: 603

Text #15

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8252. Min Act: -0.1698

Data Index: 2304129 (Open Web Text)

Max Activating Token Index: 271

Text #16

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8143. Min Act: -0.1700

Data Index: 3955958 (Open Web Text)

Max Activating Token Index: 609

Text #17

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8175. Min Act: -0.1700

Data Index: 6289123 (Open Web Text)

Max Activating Token Index: 292

Text #18

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8083. Min Act: -0.1700

Data Index: 1632739 (Open Web Text)

Max Activating Token Index: 762

Text #19

Max Range: 1.9127. Min Range: -1.9127

Max Act: 1.8086. Min Act: -0.1700

Data Index: 1632738 (Open Web Text)

Max Activating Token Index: 629