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

Dataset: Open Web Text

Neuron 2607 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: 4.7023. Min Range: -4.7023

Max Act: 4.7023. Min Act: -0.1700

Data Index: 3270683 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6979. Min Act: -0.1700

Data Index: 6226960 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6276. Min Act: -0.1700

Data Index: 5346242 (Open Web Text)

Max Activating Token Index: 437

Text #3

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6124. Min Act: -0.1700

Data Index: 4353512 (Open Web Text)

Max Activating Token Index: 526

Text #4

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6110. Min Act: -0.1700

Data Index: 270369 (Open Web Text)

Max Activating Token Index: 396

Text #5

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6553. Min Act: -0.1700

Data Index: 2302864 (Open Web Text)

Max Activating Token Index: 772

Text #6

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6408. Min Act: -0.1700

Data Index: 4025273 (Open Web Text)

Max Activating Token Index: 382

Text #7

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6237. Min Act: -0.1700

Data Index: 5597288 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5702. Min Act: -0.1700

Data Index: 5307618 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.6111. Min Act: -0.1700

Data Index: 529418 (Open Web Text)

Max Activating Token Index: 576

Text #10

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5509. Min Act: -0.1700

Data Index: 98655 (Open Web Text)

Max Activating Token Index: 923

Text #11

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5754. Min Act: -0.1700

Data Index: 265075 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5587. Min Act: -0.1700

Data Index: 1937240 (Open Web Text)

Max Activating Token Index: 296

Text #13

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5254. Min Act: -0.1700

Data Index: 4717469 (Open Web Text)

Max Activating Token Index: 293

Text #14

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5673. Min Act: -0.1700

Data Index: 2223144 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5573. Min Act: -0.1700

Data Index: 8810625 (Open Web Text)

Max Activating Token Index: 798

Text #16

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5283. Min Act: -0.1700

Data Index: 300422 (Open Web Text)

Max Activating Token Index: 562

Text #17

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.5217. Min Act: -0.1700

Data Index: 4742818 (Open Web Text)

Max Activating Token Index: 259

Text #18

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.4932. Min Act: -0.1700

Data Index: 2854225 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 4.7023. Min Range: -4.7023

Max Act: 4.4915. Min Act: -0.1700

Data Index: 926482 (Open Web Text)

Max Activating Token Index: 683