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

Dataset: Open Web Text

Neuron 1829 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: 5.1784. Min Range: -5.1784

Max Act: 5.1752. Min Act: -0.1700

Data Index: 5171066 (Open Web Text)

Max Activating Token Index: 258

Text #1

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1263. Min Act: -0.1700

Data Index: 7905342 (Open Web Text)

Max Activating Token Index: 771

Text #2

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1726. Min Act: -0.1700

Data Index: 4125360 (Open Web Text)

Max Activating Token Index: 784

Text #3

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1552. Min Act: -0.1700

Data Index: 2028787 (Open Web Text)

Max Activating Token Index: 124

Text #4

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1055. Min Act: -0.1700

Data Index: 4684822 (Open Web Text)

Max Activating Token Index: 521

Text #5

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1211. Min Act: -0.1700

Data Index: 1234970 (Open Web Text)

Max Activating Token Index: 224

Text #6

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1403. Min Act: -0.1700

Data Index: 1851325 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1784. Min Act: -0.1700

Data Index: 4578168 (Open Web Text)

Max Activating Token Index: 613

Text #8

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1005. Min Act: -0.1700

Data Index: 2036571 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0895. Min Act: -0.1700

Data Index: 1337354 (Open Web Text)

Max Activating Token Index: 293

Text #10

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0319. Min Act: -0.1699

Data Index: 5285526 (Open Web Text)

Max Activating Token Index: 732

Text #11

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0975. Min Act: -0.1700

Data Index: 5768180 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.1040. Min Act: -0.1700

Data Index: 6061487 (Open Web Text)

Max Activating Token Index: 628

Text #13

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0820. Min Act: -0.1700

Data Index: 2090741 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0266. Min Act: -0.1700

Data Index: 5576989 (Open Web Text)

Max Activating Token Index: 784

Text #15

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0645. Min Act: -0.1700

Data Index: 1140732 (Open Web Text)

Max Activating Token Index: 552

Text #16

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0244. Min Act: -0.1700

Data Index: 6135878 (Open Web Text)

Max Activating Token Index: 291

Text #17

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0586. Min Act: -0.1700

Data Index: 1973399 (Open Web Text)

Max Activating Token Index: 189

Text #18

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0436. Min Act: -0.1700

Data Index: 2374566 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 5.1784. Min Range: -5.1784

Max Act: 5.0602. Min Act: -0.1700

Data Index: 234635 (Open Web Text)

Max Activating Token Index: 37