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

Dataset: Open Web Text

Neuron 104 in Layer 2

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: 3.2527. Min Range: -3.2527

Max Act: 3.2527. Min Act: -0.1700

Data Index: 100953 (Open Web Text)

Max Activating Token Index: 532

Text #1

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2104. Min Act: -0.1700

Data Index: 8780360 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2122. Min Act: -0.1700

Data Index: 5416014 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.2059. Min Act: -0.1700

Data Index: 7519489 (Open Web Text)

Max Activating Token Index: 323

Text #4

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1949. Min Act: -0.1700

Data Index: 4962797 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1906. Min Act: -0.1700

Data Index: 3923883 (Open Web Text)

Max Activating Token Index: 133

Text #6

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1900. Min Act: -0.1700

Data Index: 7590343 (Open Web Text)

Max Activating Token Index: 935

Text #7

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1792. Min Act: -0.1700

Data Index: 4896223 (Open Web Text)

Max Activating Token Index: 250

Text #8

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1618. Min Act: -0.1700

Data Index: 3756585 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1540. Min Act: -0.1700

Data Index: 4862003 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1792. Min Act: -0.1700

Data Index: 3204849 (Open Web Text)

Max Activating Token Index: 274

Text #11

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1539. Min Act: -0.1700

Data Index: 8260448 (Open Web Text)

Max Activating Token Index: 447

Text #12

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1641. Min Act: -0.1700

Data Index: 5647166 (Open Web Text)

Max Activating Token Index: 428

Text #13

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1275. Min Act: -0.1700

Data Index: 5977541 (Open Web Text)

Max Activating Token Index: 90

Text #14

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1367. Min Act: -0.1700

Data Index: 2866288 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1443. Min Act: -0.1700

Data Index: 3415646 (Open Web Text)

Max Activating Token Index: 218

Text #16

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1686177 (Open Web Text)

Max Activating Token Index: 460

Text #17

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1328. Min Act: -0.1700

Data Index: 5906659 (Open Web Text)

Max Activating Token Index: 889

Text #18

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1472. Min Act: -0.1700

Data Index: 6308354 (Open Web Text)

Max Activating Token Index: 136

Text #19

Max Range: 3.2527. Min Range: -3.2527

Max Act: 3.1482. Min Act: -0.1700

Data Index: 4164995 (Open Web Text)

Max Activating Token Index: 402