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

Dataset: Open Web Text

Neuron 2302 in Layer 4

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: 3.1451. Min Range: -3.1451

Max Act: 3.1283. Min Act: -0.1700

Data Index: 3227448 (Open Web Text)

Max Activating Token Index: 650

Text #1

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1451. Min Act: -0.1700

Data Index: 695400 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.1080. Min Act: -0.1700

Data Index: 8171981 (Open Web Text)

Max Activating Token Index: 986

Text #3

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0892. Min Act: -0.1700

Data Index: 3629522 (Open Web Text)

Max Activating Token Index: 168

Text #4

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0590. Min Act: -0.1700

Data Index: 7690638 (Open Web Text)

Max Activating Token Index: 799

Text #5

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0558. Min Act: -0.1700

Data Index: 3519307 (Open Web Text)

Max Activating Token Index: 183

Text #6

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0571. Min Act: -0.1700

Data Index: 2290723 (Open Web Text)

Max Activating Token Index: 840

Text #7

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0396. Min Act: -0.1700

Data Index: 2411149 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0107. Min Act: -0.1700

Data Index: 1041694 (Open Web Text)

Max Activating Token Index: 683

Text #9

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0169. Min Act: -0.1700

Data Index: 3648847 (Open Web Text)

Max Activating Token Index: 859

Text #10

Max Range: 3.1451. Min Range: -3.1451

Max Act: 3.0182. Min Act: -0.1700

Data Index: 601120 (Open Web Text)

Max Activating Token Index: 1005

Text #11

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9971. Min Act: -0.1700

Data Index: 8217189 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9854. Min Act: -0.1700

Data Index: 7589114 (Open Web Text)

Max Activating Token Index: 225

Text #13

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9964. Min Act: -0.1700

Data Index: 4575607 (Open Web Text)

Max Activating Token Index: 976

Text #14

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9973. Min Act: -0.1700

Data Index: 4929939 (Open Web Text)

Max Activating Token Index: 237

Text #15

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9883. Min Act: -0.1700

Data Index: 183834 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9737. Min Act: -0.1700

Data Index: 1356969 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9660. Min Act: -0.1700

Data Index: 7899105 (Open Web Text)

Max Activating Token Index: 184

Text #18

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9515. Min Act: -0.1700

Data Index: 1872012 (Open Web Text)

Max Activating Token Index: 510

Text #19

Max Range: 3.1451. Min Range: -3.1451

Max Act: 2.9715. Min Act: -0.1700

Data Index: 7042969 (Open Web Text)

Max Activating Token Index: 296