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

Dataset: Open Web Text

Neuron 2433 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: 4.1811. Min Range: -4.1811

Max Act: 4.1811. Min Act: -0.1700

Data Index: 6013029 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.5567. Min Act: -0.1700

Data Index: 2785512 (Open Web Text)

Max Activating Token Index: 388

Text #2

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.5580. Min Act: -0.1700

Data Index: 6169896 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.5138. Min Act: -0.1700

Data Index: 7128842 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4764. Min Act: -0.1700

Data Index: 3665463 (Open Web Text)

Max Activating Token Index: 872

Text #5

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4818. Min Act: -0.1700

Data Index: 5828252 (Open Web Text)

Max Activating Token Index: 223

Text #6

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4557. Min Act: -0.1700

Data Index: 5550961 (Open Web Text)

Max Activating Token Index: 99

Text #7

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4641. Min Act: -0.1700

Data Index: 5564429 (Open Web Text)

Max Activating Token Index: 320

Text #8

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4798. Min Act: -0.1700

Data Index: 1962371 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4499. Min Act: -0.1700

Data Index: 2293074 (Open Web Text)

Max Activating Token Index: 179

Text #10

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4208. Min Act: -0.1700

Data Index: 7177295 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3950. Min Act: -0.1700

Data Index: 8801204 (Open Web Text)

Max Activating Token Index: 418

Text #12

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.4128. Min Act: -0.1700

Data Index: 4049599 (Open Web Text)

Max Activating Token Index: 422

Text #13

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3812. Min Act: -0.1700

Data Index: 5214384 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3905. Min Act: -0.1700

Data Index: 1279489 (Open Web Text)

Max Activating Token Index: 253

Text #15

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3757. Min Act: -0.1700

Data Index: 5357446 (Open Web Text)

Max Activating Token Index: 12

Text #16

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3698. Min Act: -0.1700

Data Index: 2372073 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3886. Min Act: -0.1700

Data Index: 8384926 (Open Web Text)

Max Activating Token Index: 501

Text #18

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3233. Min Act: -0.1700

Data Index: 5823091 (Open Web Text)

Max Activating Token Index: 123

Text #19

Max Range: 4.1811. Min Range: -4.1811

Max Act: 3.3545. Min Act: -0.1700

Data Index: 3044279 (Open Web Text)

Max Activating Token Index: 206