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

Dataset: Open Web Text

Neuron 2378 in Layer 3

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: 4.3045. Min Range: -4.3045

Max Act: 4.3045. Min Act: -0.1700

Data Index: 1752565 (Open Web Text)

Max Activating Token Index: 447

Text #1

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2633. Min Act: -0.1700

Data Index: 8666606 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2743. Min Act: -0.1700

Data Index: 2034802 (Open Web Text)

Max Activating Token Index: 796

Text #3

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1990. Min Act: -0.1700

Data Index: 4489113 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.3013. Min Act: -0.1700

Data Index: 3905600 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1898. Min Act: -0.1700

Data Index: 2424542 (Open Web Text)

Max Activating Token Index: 217

Text #6

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1963. Min Act: -0.1700

Data Index: 1906000 (Open Web Text)

Max Activating Token Index: 389

Text #7

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2015. Min Act: -0.1700

Data Index: 2481197 (Open Web Text)

Max Activating Token Index: 324

Text #8

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2229. Min Act: -0.1700

Data Index: 8773708 (Open Web Text)

Max Activating Token Index: 321

Text #9

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2572. Min Act: -0.1700

Data Index: 8566565 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1797. Min Act: -0.1700

Data Index: 3548809 (Open Web Text)

Max Activating Token Index: 930

Text #11

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2339. Min Act: -0.1700

Data Index: 2412315 (Open Web Text)

Max Activating Token Index: 271

Text #12

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1725. Min Act: -0.1700

Data Index: 7837144 (Open Web Text)

Max Activating Token Index: 254

Text #13

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2136. Min Act: -0.1700

Data Index: 1682737 (Open Web Text)

Max Activating Token Index: 566

Text #14

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1618. Min Act: -0.1700

Data Index: 6218826 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2011. Min Act: -0.1700

Data Index: 3631661 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2002. Min Act: -0.1700

Data Index: 17134 (Open Web Text)

Max Activating Token Index: 533

Text #17

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.2163. Min Act: -0.1700

Data Index: 5914359 (Open Web Text)

Max Activating Token Index: 486

Text #18

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1441. Min Act: -0.1700

Data Index: 648770 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 4.3045. Min Range: -4.3045

Max Act: 4.1546. Min Act: -0.1700

Data Index: 465578 (Open Web Text)

Max Activating Token Index: 780