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

Dataset: Open Web Text

Neuron 1726 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: 3.7545. Min Range: -3.7545

Max Act: 3.7545. Min Act: -0.1700

Data Index: 948162 (Open Web Text)

Max Activating Token Index: 809

Text #1

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5904. Min Act: -0.1700

Data Index: 5563035 (Open Web Text)

Max Activating Token Index: 322

Text #2

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5477. Min Act: -0.1700

Data Index: 149533 (Open Web Text)

Max Activating Token Index: 298

Text #3

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5065. Min Act: -0.1700

Data Index: 3615340 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5405. Min Act: -0.1700

Data Index: 3673529 (Open Web Text)

Max Activating Token Index: 683

Text #5

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4945. Min Act: -0.1700

Data Index: 8520521 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4956. Min Act: -0.1700

Data Index: 4100355 (Open Web Text)

Max Activating Token Index: 325

Text #7

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5021. Min Act: -0.1700

Data Index: 3183230 (Open Web Text)

Max Activating Token Index: 883

Text #8

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.5242. Min Act: -0.1700

Data Index: 8059519 (Open Web Text)

Max Activating Token Index: 668

Text #9

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4616. Min Act: -0.1700

Data Index: 961183 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4339. Min Act: -0.1700

Data Index: 1421226 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.3821. Min Act: -0.1700

Data Index: 4771474 (Open Web Text)

Max Activating Token Index: 421

Text #12

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4515. Min Act: -0.1700

Data Index: 4127464 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4003. Min Act: -0.1700

Data Index: 5200202 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.3733. Min Act: -0.1700

Data Index: 3647387 (Open Web Text)

Max Activating Token Index: 884

Text #15

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4155. Min Act: -0.1700

Data Index: 1871921 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.4023. Min Act: -0.1700

Data Index: 3706524 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.3898. Min Act: -0.1700

Data Index: 2888584 (Open Web Text)

Max Activating Token Index: 450

Text #18

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.3890. Min Act: -0.1700

Data Index: 2237040 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 3.7545. Min Range: -3.7545

Max Act: 3.3969. Min Act: -0.1700

Data Index: 5632496 (Open Web Text)

Max Activating Token Index: 65