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

Dataset: Open Web Text

Neuron 3068 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: 2.2007. Min Range: -2.2007

Max Act: 2.2005. Min Act: -0.1700

Data Index: 1439196 (Open Web Text)

Max Activating Token Index: 443

Text #1

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.2007. Min Act: -0.1700

Data Index: 2681530 (Open Web Text)

Max Activating Token Index: 43

Text #2

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1953. Min Act: -0.1700

Data Index: 8377377 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1858. Min Act: -0.1700

Data Index: 1193948 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1860. Min Act: -0.1700

Data Index: 6671442 (Open Web Text)

Max Activating Token Index: 508

Text #5

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1732. Min Act: -0.1700

Data Index: 5048832 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1822. Min Act: -0.1700

Data Index: 430696 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1710. Min Act: -0.1700

Data Index: 6983416 (Open Web Text)

Max Activating Token Index: 109

Text #8

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1863. Min Act: -0.1700

Data Index: 5785925 (Open Web Text)

Max Activating Token Index: 224

Text #9

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1702. Min Act: -0.1700

Data Index: 1480259 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1519. Min Act: -0.1700

Data Index: 3469930 (Open Web Text)

Max Activating Token Index: 72

Text #11

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1529. Min Act: -0.1700

Data Index: 2090701 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1604. Min Act: -0.1700

Data Index: 6265275 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1463. Min Act: -0.1700

Data Index: 7478025 (Open Web Text)

Max Activating Token Index: 27

Text #14

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1681. Min Act: -0.1700

Data Index: 8099412 (Open Web Text)

Max Activating Token Index: 202

Text #15

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1658. Min Act: -0.1700

Data Index: 8574279 (Open Web Text)

Max Activating Token Index: 708

Text #16

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1514. Min Act: -0.1700

Data Index: 5539491 (Open Web Text)

Max Activating Token Index: 493

Text #17

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1525. Min Act: -0.1700

Data Index: 5311167 (Open Web Text)

Max Activating Token Index: 892

Text #18

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1369. Min Act: -0.1700

Data Index: 702266 (Open Web Text)

Max Activating Token Index: 397

Text #19

Max Range: 2.2007. Min Range: -2.2007

Max Act: 2.1403. Min Act: -0.1700

Data Index: 232145 (Open Web Text)

Max Activating Token Index: 190