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

Dataset: Open Web Text

Neuron 2070 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: 4.4578. Min Range: -4.4578

Max Act: 4.4578. Min Act: -0.1698

Data Index: 6166037 (Open Web Text)

Max Activating Token Index: 423

Text #1

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.4503. Min Act: -0.1700

Data Index: 6725334 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2989. Min Act: -0.1700

Data Index: 3034632 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.3041. Min Act: -0.1700

Data Index: 4176870 (Open Web Text)

Max Activating Token Index: 256

Text #4

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2617. Min Act: -0.1700

Data Index: 6191717 (Open Web Text)

Max Activating Token Index: 537

Text #5

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.3040. Min Act: -0.1700

Data Index: 8732667 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.3123. Min Act: -0.1700

Data Index: 2633686 (Open Web Text)

Max Activating Token Index: 272

Text #7

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2556. Min Act: -0.1700

Data Index: 4154856 (Open Web Text)

Max Activating Token Index: 899

Text #8

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2715. Min Act: -0.1699

Data Index: 7345423 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2631. Min Act: -0.1700

Data Index: 4886245 (Open Web Text)

Max Activating Token Index: 556

Text #10

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2581. Min Act: -0.1698

Data Index: 6977318 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2459. Min Act: -0.1700

Data Index: 2689913 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2477. Min Act: -0.1700

Data Index: 8401672 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2173. Min Act: -0.1700

Data Index: 8321770 (Open Web Text)

Max Activating Token Index: 313

Text #14

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2712. Min Act: -0.1699

Data Index: 7684652 (Open Web Text)

Max Activating Token Index: 274

Text #15

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2075. Min Act: -0.1700

Data Index: 2756210 (Open Web Text)

Max Activating Token Index: 351

Text #16

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2283. Min Act: -0.1700

Data Index: 2341037 (Open Web Text)

Max Activating Token Index: 294

Text #17

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.1830. Min Act: -0.1700

Data Index: 7012911 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.1588. Min Act: -0.1700

Data Index: 4060158 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 4.4578. Min Range: -4.4578

Max Act: 4.2186. Min Act: -0.1700

Data Index: 1753226 (Open Web Text)

Max Activating Token Index: 313