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

Dataset: Open Web Text

Neuron 2020 in Layer 1

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: 4.6575. Min Range: -4.6575

Max Act: 4.6575. Min Act: -0.1700

Data Index: 785461 (Open Web Text)

Max Activating Token Index: 861

Text #1

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6414. Min Act: -0.1700

Data Index: 6988528 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6358. Min Act: -0.1700

Data Index: 7425286 (Open Web Text)

Max Activating Token Index: 855

Text #3

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6189. Min Act: -0.1700

Data Index: 8457857 (Open Web Text)

Max Activating Token Index: 544

Text #4

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6368. Min Act: -0.1700

Data Index: 7778223 (Open Web Text)

Max Activating Token Index: 565

Text #5

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6144. Min Act: -0.1700

Data Index: 2690272 (Open Web Text)

Max Activating Token Index: 459

Text #6

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5929. Min Act: -0.1700

Data Index: 5442312 (Open Web Text)

Max Activating Token Index: 492

Text #7

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5852. Min Act: -0.1700

Data Index: 1278238 (Open Web Text)

Max Activating Token Index: 496

Text #8

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5953. Min Act: -0.1700

Data Index: 5118933 (Open Web Text)

Max Activating Token Index: 575

Text #9

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5809. Min Act: -0.1700

Data Index: 4730199 (Open Web Text)

Max Activating Token Index: 397

Text #10

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.6167. Min Act: -0.1700

Data Index: 8767088 (Open Web Text)

Max Activating Token Index: 306

Text #11

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5979. Min Act: -0.1700

Data Index: 2423913 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5837. Min Act: -0.1700

Data Index: 3078481 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5904. Min Act: -0.1700

Data Index: 6048307 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5624. Min Act: -0.1700

Data Index: 7998790 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5568. Min Act: -0.1700

Data Index: 1233400 (Open Web Text)

Max Activating Token Index: 129

Text #16

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5813. Min Act: -0.1700

Data Index: 3426126 (Open Web Text)

Max Activating Token Index: 667

Text #17

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5651. Min Act: -0.1700

Data Index: 4557659 (Open Web Text)

Max Activating Token Index: 946

Text #18

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5579. Min Act: -0.1700

Data Index: 7748087 (Open Web Text)

Max Activating Token Index: 534

Text #19

Max Range: 4.6575. Min Range: -4.6575

Max Act: 4.5560. Min Act: -0.1700

Data Index: 2825062 (Open Web Text)

Max Activating Token Index: 775