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

Dataset: Open Web Text

Neuron 797 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: 2.0022. Min Range: -2.0022

Max Act: 2.0022. Min Act: -0.1700

Data Index: 7130924 (Open Web Text)

Max Activating Token Index: 232

Text #1

Max Range: 2.0022. Min Range: -2.0022

Max Act: 2.0007. Min Act: -0.1700

Data Index: 1101280 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9867. Min Act: -0.1700

Data Index: 4340837 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9559. Min Act: -0.1700

Data Index: 2367195 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9455. Min Act: -0.1700

Data Index: 254589 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9465. Min Act: -0.1700

Data Index: 5215637 (Open Web Text)

Max Activating Token Index: 414

Text #6

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9410. Min Act: -0.1700

Data Index: 5339787 (Open Web Text)

Max Activating Token Index: 418

Text #7

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9338. Min Act: -0.1700

Data Index: 3360442 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9427. Min Act: -0.1700

Data Index: 4801818 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9380. Min Act: -0.1700

Data Index: 22342 (Open Web Text)

Max Activating Token Index: 870

Text #10

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9363. Min Act: -0.1700

Data Index: 5372850 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9282. Min Act: -0.1700

Data Index: 7781882 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9265. Min Act: -0.1700

Data Index: 7781883 (Open Web Text)

Max Activating Token Index: 678

Text #13

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9303. Min Act: -0.1700

Data Index: 1614445 (Open Web Text)

Max Activating Token Index: 192

Text #14

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9261. Min Act: -0.1700

Data Index: 3901506 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9250. Min Act: -0.1700

Data Index: 6599253 (Open Web Text)

Max Activating Token Index: 248

Text #16

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9287. Min Act: -0.1700

Data Index: 2601109 (Open Web Text)

Max Activating Token Index: 189

Text #17

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9240. Min Act: -0.1700

Data Index: 6738821 (Open Web Text)

Max Activating Token Index: 699

Text #18

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9222. Min Act: -0.1700

Data Index: 5022941 (Open Web Text)

Max Activating Token Index: 958

Text #19

Max Range: 2.0022. Min Range: -2.0022

Max Act: 1.9170. Min Act: -0.1700

Data Index: 1813127 (Open Web Text)

Max Activating Token Index: 85