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

Dataset: Open Web Text

Neuron 2930 in Layer 5

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: 6.0377. Min Range: -6.0377

Max Act: 6.0377. Min Act: -0.1700

Data Index: 1399937 (Open Web Text)

Max Activating Token Index: 665

Text #1

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.9950. Min Act: -0.1700

Data Index: 3017941 (Open Web Text)

Max Activating Token Index: 695

Text #2

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.9649. Min Act: -0.1700

Data Index: 3921509 (Open Web Text)

Max Activating Token Index: 242

Text #3

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.9803. Min Act: -0.1700

Data Index: 3054732 (Open Web Text)

Max Activating Token Index: 740

Text #4

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.7163. Min Act: -0.1700

Data Index: 6658557 (Open Web Text)

Max Activating Token Index: 987

Text #5

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.6951. Min Act: -0.1700

Data Index: 384869 (Open Web Text)

Max Activating Token Index: 356

Text #6

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.7316. Min Act: -0.1700

Data Index: 8695222 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.6071. Min Act: -0.1700

Data Index: 6969672 (Open Web Text)

Max Activating Token Index: 616

Text #8

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.5986. Min Act: -0.1700

Data Index: 8755512 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.5465. Min Act: -0.1700

Data Index: 7521361 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.5328. Min Act: -0.1700

Data Index: 6041051 (Open Web Text)

Max Activating Token Index: 824

Text #11

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4923. Min Act: -0.1700

Data Index: 8501263 (Open Web Text)

Max Activating Token Index: 247

Text #12

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4918. Min Act: -0.1700

Data Index: 7757220 (Open Web Text)

Max Activating Token Index: 945

Text #13

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4362. Min Act: -0.1700

Data Index: 7255908 (Open Web Text)

Max Activating Token Index: 932

Text #14

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4750. Min Act: -0.1700

Data Index: 2173780 (Open Web Text)

Max Activating Token Index: 406

Text #15

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4718. Min Act: -0.1700

Data Index: 7498601 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4205. Min Act: -0.1700

Data Index: 1655221 (Open Web Text)

Max Activating Token Index: 479

Text #17

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4291. Min Act: -0.1700

Data Index: 2670048 (Open Web Text)

Max Activating Token Index: 363

Text #18

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.4389. Min Act: -0.1700

Data Index: 8264984 (Open Web Text)

Max Activating Token Index: 445

Text #19

Max Range: 6.0377. Min Range: -6.0377

Max Act: 5.3804. Min Act: -0.1700

Data Index: 107056 (Open Web Text)

Max Activating Token Index: 151