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

Dataset: Open Web Text

Neuron 2748 in Layer 1

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: 1.9505. Min Range: -1.9505

Max Act: 1.9505. Min Act: -0.1700

Data Index: 457920 (Open Web Text)

Max Activating Token Index: 291

Text #1

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.9014. Min Act: -0.1700

Data Index: 8475602 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8981. Min Act: -0.1699

Data Index: 3572381 (Open Web Text)

Max Activating Token Index: 763

Text #3

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8746. Min Act: -0.1700

Data Index: 2628757 (Open Web Text)

Max Activating Token Index: 638

Text #4

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8865. Min Act: -0.1700

Data Index: 7671981 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8574. Min Act: -0.1700

Data Index: 8725398 (Open Web Text)

Max Activating Token Index: 490

Text #6

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8429. Min Act: -0.1700

Data Index: 630508 (Open Web Text)

Max Activating Token Index: 254

Text #7

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8415. Min Act: -0.1696

Data Index: 6267843 (Open Web Text)

Max Activating Token Index: 724

Text #8

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8343. Min Act: -0.1699

Data Index: 6863370 (Open Web Text)

Max Activating Token Index: 785

Text #9

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8306. Min Act: -0.1699

Data Index: 1412422 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8445. Min Act: -0.1700

Data Index: 260931 (Open Web Text)

Max Activating Token Index: 143

Text #11

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8347. Min Act: -0.1700

Data Index: 7009536 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8269. Min Act: -0.1700

Data Index: 8744976 (Open Web Text)

Max Activating Token Index: 772

Text #13

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8335. Min Act: -0.1700

Data Index: 6132261 (Open Web Text)

Max Activating Token Index: 93

Text #14

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8338. Min Act: -0.1700

Data Index: 880161 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8378. Min Act: -0.1700

Data Index: 6889856 (Open Web Text)

Max Activating Token Index: 862

Text #16

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8333. Min Act: -0.1700

Data Index: 1134581 (Open Web Text)

Max Activating Token Index: 180

Text #17

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8349. Min Act: -0.1700

Data Index: 5680839 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8236. Min Act: -0.1700

Data Index: 5420899 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 1.9505. Min Range: -1.9505

Max Act: 1.8281. Min Act: -0.1691

Data Index: 633076 (Open Web Text)

Max Activating Token Index: 887