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

Dataset: Open Web Text

Neuron 2435 in Layer 6

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: 3.9896. Min Range: -3.9896

Max Act: 3.9896. Min Act: -0.1700

Data Index: 1928752 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7332. Min Act: -0.1700

Data Index: 8581066 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7535. Min Act: -0.1700

Data Index: 5161659 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7548. Min Act: -0.1700

Data Index: 6775548 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7364. Min Act: -0.1700

Data Index: 1975390 (Open Web Text)

Max Activating Token Index: 37

Text #5

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.6829. Min Act: -0.1700

Data Index: 5176683 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.6533. Min Act: -0.1700

Data Index: 7939045 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.6489. Min Act: -0.1700

Data Index: 378644 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.6155. Min Act: -0.1700

Data Index: 3278248 (Open Web Text)

Max Activating Token Index: 931

Text #9

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5991. Min Act: -0.1700

Data Index: 606379 (Open Web Text)

Max Activating Token Index: 565

Text #10

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5712. Min Act: -0.1700

Data Index: 6743375 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5659. Min Act: -0.1700

Data Index: 5671751 (Open Web Text)

Max Activating Token Index: 297

Text #12

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5760. Min Act: -0.1700

Data Index: 5299694 (Open Web Text)

Max Activating Token Index: 918

Text #13

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5520. Min Act: -0.1700

Data Index: 353026 (Open Web Text)

Max Activating Token Index: 36

Text #14

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5660. Min Act: -0.1700

Data Index: 4636289 (Open Web Text)

Max Activating Token Index: 328

Text #15

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5094. Min Act: -0.1700

Data Index: 2957303 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5260. Min Act: -0.1700

Data Index: 8740147 (Open Web Text)

Max Activating Token Index: 728

Text #17

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5013. Min Act: -0.1700

Data Index: 1107867 (Open Web Text)

Max Activating Token Index: 251

Text #18

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.4908. Min Act: -0.1700

Data Index: 4835217 (Open Web Text)

Max Activating Token Index: 728

Text #19

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.5282. Min Act: -0.1700

Data Index: 5427942 (Open Web Text)

Max Activating Token Index: 172