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

Dataset: Open Web Text

Neuron 2757 in Layer 4

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: 4.6564. Min Range: -4.6564

Max Act: 4.6301. Min Act: -0.1700

Data Index: 815962 (Open Web Text)

Max Activating Token Index: 475

Text #1

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.6322. Min Act: -0.1700

Data Index: 8357724 (Open Web Text)

Max Activating Token Index: 896

Text #2

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.6564. Min Act: -0.1700

Data Index: 5566882 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.6294. Min Act: -0.1700

Data Index: 6072579 (Open Web Text)

Max Activating Token Index: 371

Text #4

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.5680. Min Act: -0.1700

Data Index: 636308 (Open Web Text)

Max Activating Token Index: 398

Text #5

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.5248. Min Act: -0.1700

Data Index: 7091715 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.5483. Min Act: -0.1700

Data Index: 882140 (Open Web Text)

Max Activating Token Index: 694

Text #7

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.5456. Min Act: -0.1700

Data Index: 14304 (Open Web Text)

Max Activating Token Index: 690

Text #8

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.5124. Min Act: -0.1700

Data Index: 1625796 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4857. Min Act: -0.1700

Data Index: 6264674 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4643. Min Act: -0.1700

Data Index: 4539403 (Open Web Text)

Max Activating Token Index: 744

Text #11

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4325. Min Act: -0.1700

Data Index: 1397608 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4301. Min Act: -0.1700

Data Index: 3426792 (Open Web Text)

Max Activating Token Index: 487

Text #13

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4119. Min Act: -0.1700

Data Index: 711928 (Open Web Text)

Max Activating Token Index: 1002

Text #14

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4492. Min Act: -0.1700

Data Index: 2499835 (Open Web Text)

Max Activating Token Index: 587

Text #15

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.4376. Min Act: -0.1700

Data Index: 6939646 (Open Web Text)

Max Activating Token Index: 970

Text #16

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.3585. Min Act: -0.1700

Data Index: 3538781 (Open Web Text)

Max Activating Token Index: 184

Text #17

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.3676. Min Act: -0.1700

Data Index: 7658530 (Open Web Text)

Max Activating Token Index: 314

Text #18

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.3691. Min Act: -0.1700

Data Index: 7347687 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 4.6564. Min Range: -4.6564

Max Act: 4.3357. Min Act: -0.1700

Data Index: 5862065 (Open Web Text)

Max Activating Token Index: 377