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

Dataset: Open Web Text

Neuron 401 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: 5.1800. Min Range: -5.1800

Max Act: 5.1800. Min Act: -0.1700

Data Index: 8310057 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.7368. Min Act: -0.1700

Data Index: 7165050 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5894. Min Act: -0.1700

Data Index: 1722198 (Open Web Text)

Max Activating Token Index: 776

Text #3

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5605. Min Act: -0.1700

Data Index: 300332 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5607. Min Act: -0.1700

Data Index: 5032422 (Open Web Text)

Max Activating Token Index: 225

Text #5

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5850. Min Act: -0.1700

Data Index: 1618454 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5934. Min Act: -0.1700

Data Index: 1002136 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5580. Min Act: -0.1700

Data Index: 1319874 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5008. Min Act: -0.1700

Data Index: 640017 (Open Web Text)

Max Activating Token Index: 245

Text #9

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5027. Min Act: -0.1700

Data Index: 7340305 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.4863. Min Act: -0.1700

Data Index: 7340304 (Open Web Text)

Max Activating Token Index: 289

Text #11

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.4180. Min Act: -0.1700

Data Index: 1390458 (Open Web Text)

Max Activating Token Index: 213

Text #12

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.5793. Min Act: -0.1700

Data Index: 6898061 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.4815. Min Act: -0.1700

Data Index: 250215 (Open Web Text)

Max Activating Token Index: 608

Text #14

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.4517. Min Act: -0.1700

Data Index: 2747470 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.3719. Min Act: -0.1700

Data Index: 1711050 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.4498. Min Act: -0.1700

Data Index: 1722200 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.3925. Min Act: -0.1700

Data Index: 8354265 (Open Web Text)

Max Activating Token Index: 217

Text #18

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.3519. Min Act: -0.1700

Data Index: 7456864 (Open Web Text)

Max Activating Token Index: 93

Text #19

Max Range: 5.1800. Min Range: -5.1800

Max Act: 4.3823. Min Act: -0.1700

Data Index: 4172354 (Open Web Text)

Max Activating Token Index: 251