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

Dataset: Open Web Text

Neuron 2199 in Layer 3

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: 4.4730. Min Range: -4.4730

Max Act: 4.4730. Min Act: -0.1700

Data Index: 814280 (Open Web Text)

Max Activating Token Index: 836

Text #1

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.4039. Min Act: -0.1700

Data Index: 385961 (Open Web Text)

Max Activating Token Index: 315

Text #2

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3906. Min Act: -0.1700

Data Index: 1452601 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3483. Min Act: -0.1700

Data Index: 2559041 (Open Web Text)

Max Activating Token Index: 775

Text #4

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3210. Min Act: -0.1700

Data Index: 8603961 (Open Web Text)

Max Activating Token Index: 256

Text #5

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3254. Min Act: -0.1700

Data Index: 5846245 (Open Web Text)

Max Activating Token Index: 655

Text #6

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3150. Min Act: -0.1700

Data Index: 534582 (Open Web Text)

Max Activating Token Index: 304

Text #7

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.3056. Min Act: -0.1700

Data Index: 2648982 (Open Web Text)

Max Activating Token Index: 267

Text #8

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2926. Min Act: -0.1700

Data Index: 7903514 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2460. Min Act: -0.1700

Data Index: 4932311 (Open Web Text)

Max Activating Token Index: 824

Text #10

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2111. Min Act: -0.1700

Data Index: 1410253 (Open Web Text)

Max Activating Token Index: 472

Text #11

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2307. Min Act: -0.1700

Data Index: 3943708 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2587. Min Act: -0.1700

Data Index: 4172603 (Open Web Text)

Max Activating Token Index: 403

Text #13

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2430. Min Act: -0.1700

Data Index: 3180399 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2001. Min Act: -0.1700

Data Index: 1637429 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2308. Min Act: -0.1700

Data Index: 1131358 (Open Web Text)

Max Activating Token Index: 636

Text #16

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2104. Min Act: -0.1700

Data Index: 3824358 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2097. Min Act: -0.1700

Data Index: 4493140 (Open Web Text)

Max Activating Token Index: 955

Text #18

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2011. Min Act: -0.1700

Data Index: 3320562 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 4.4730. Min Range: -4.4730

Max Act: 4.2123. Min Act: -0.1700

Data Index: 6352736 (Open Web Text)

Max Activating Token Index: 937