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

Dataset: Open Web Text

Neuron 1937 in Layer 5

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: 5.7097. Min Range: -5.7097

Max Act: 5.7097. Min Act: -0.1700

Data Index: 5495261 (Open Web Text)

Max Activating Token Index: 336

Text #1

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.5654. Min Act: -0.1700

Data Index: 1843396 (Open Web Text)

Max Activating Token Index: 754

Text #2

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.5145. Min Act: -0.1700

Data Index: 7501320 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.5232. Min Act: -0.1700

Data Index: 5643168 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4748. Min Act: -0.1700

Data Index: 8394433 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4299. Min Act: -0.1700

Data Index: 1178676 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4709. Min Act: -0.1700

Data Index: 5818465 (Open Web Text)

Max Activating Token Index: 566

Text #7

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4503. Min Act: -0.1700

Data Index: 570675 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4520. Min Act: -0.1700

Data Index: 6830037 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4521. Min Act: -0.1700

Data Index: 2852499 (Open Web Text)

Max Activating Token Index: 988

Text #10

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4223. Min Act: -0.1700

Data Index: 5830548 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4378. Min Act: -0.1700

Data Index: 2340902 (Open Web Text)

Max Activating Token Index: 378

Text #12

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.3860. Min Act: -0.1700

Data Index: 826609 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4643. Min Act: -0.1700

Data Index: 1594075 (Open Web Text)

Max Activating Token Index: 768

Text #14

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.3912. Min Act: -0.1700

Data Index: 7091376 (Open Web Text)

Max Activating Token Index: 598

Text #15

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4114. Min Act: -0.1700

Data Index: 3515815 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.3719. Min Act: -0.1700

Data Index: 6440062 (Open Web Text)

Max Activating Token Index: 462

Text #17

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.3833. Min Act: -0.1700

Data Index: 677285 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.4121. Min Act: -0.1700

Data Index: 4635900 (Open Web Text)

Max Activating Token Index: 477

Text #19

Max Range: 5.7097. Min Range: -5.7097

Max Act: 5.3800. Min Act: -0.1700

Data Index: 1904947 (Open Web Text)

Max Activating Token Index: 587