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

Dataset: Open Web Text

Neuron 2558 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: 3.6971. Min Range: -3.6971

Max Act: 3.6971. Min Act: -0.1700

Data Index: 754429 (Open Web Text)

Max Activating Token Index: 682

Text #1

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5744. Min Act: -0.1700

Data Index: 7474655 (Open Web Text)

Max Activating Token Index: 959

Text #2

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5291. Min Act: -0.1700

Data Index: 2734054 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5043. Min Act: -0.1700

Data Index: 7266979 (Open Web Text)

Max Activating Token Index: 789

Text #4

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5040. Min Act: -0.1700

Data Index: 1060437 (Open Web Text)

Max Activating Token Index: 484

Text #5

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5007. Min Act: -0.1700

Data Index: 4849726 (Open Web Text)

Max Activating Token Index: 566

Text #6

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4828. Min Act: -0.1700

Data Index: 4237732 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.5010. Min Act: -0.1700

Data Index: 6967037 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4362. Min Act: -0.1700

Data Index: 1836114 (Open Web Text)

Max Activating Token Index: 632

Text #9

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4718. Min Act: -0.1700

Data Index: 6576845 (Open Web Text)

Max Activating Token Index: 563

Text #10

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4518. Min Act: -0.1700

Data Index: 162039 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4182. Min Act: -0.1700

Data Index: 8089021 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4353. Min Act: -0.1700

Data Index: 6070209 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.3529. Min Act: -0.1700

Data Index: 1034510 (Open Web Text)

Max Activating Token Index: 719

Text #14

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.3928. Min Act: -0.1700

Data Index: 659032 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.3921. Min Act: -0.1700

Data Index: 7252147 (Open Web Text)

Max Activating Token Index: 452

Text #16

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.3894. Min Act: -0.1700

Data Index: 2748638 (Open Web Text)

Max Activating Token Index: 55

Text #17

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.3710. Min Act: -0.1700

Data Index: 2825654 (Open Web Text)

Max Activating Token Index: 426

Text #18

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4021. Min Act: -0.1700

Data Index: 2328056 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 3.6971. Min Range: -3.6971

Max Act: 3.4061. Min Act: -0.1700

Data Index: 5027172 (Open Web Text)

Max Activating Token Index: 821