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

Dataset: Open Web Text

Neuron 613 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: 4.6728. Min Range: -4.6728

Max Act: 4.6728. Min Act: -0.1700

Data Index: 5537116 (Open Web Text)

Max Activating Token Index: 763

Text #1

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.5379. Min Act: -0.1700

Data Index: 2800446 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.5255. Min Act: -0.1700

Data Index: 4349274 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4945. Min Act: -0.1700

Data Index: 4418652 (Open Web Text)

Max Activating Token Index: 924

Text #4

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4879. Min Act: -0.1700

Data Index: 5200409 (Open Web Text)

Max Activating Token Index: 627

Text #5

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4325. Min Act: -0.1700

Data Index: 534507 (Open Web Text)

Max Activating Token Index: 502

Text #6

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4416. Min Act: -0.1700

Data Index: 3586448 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4516. Min Act: -0.1700

Data Index: 7599979 (Open Web Text)

Max Activating Token Index: 61

Text #8

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4516. Min Act: -0.1700

Data Index: 870740 (Open Web Text)

Max Activating Token Index: 715

Text #9

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4197. Min Act: -0.1700

Data Index: 232961 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4144. Min Act: -0.1700

Data Index: 535281 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4132. Min Act: -0.1700

Data Index: 4131614 (Open Web Text)

Max Activating Token Index: 796

Text #12

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4482. Min Act: -0.1700

Data Index: 3896695 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4302. Min Act: -0.1700

Data Index: 5964296 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4138. Min Act: -0.1700

Data Index: 5397106 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4346. Min Act: -0.1700

Data Index: 3215213 (Open Web Text)

Max Activating Token Index: 640

Text #16

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.4218. Min Act: -0.1700

Data Index: 4498028 (Open Web Text)

Max Activating Token Index: 637

Text #17

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.3491. Min Act: -0.1700

Data Index: 317376 (Open Web Text)

Max Activating Token Index: 442

Text #18

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.3928. Min Act: -0.1700

Data Index: 902997 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 4.6728. Min Range: -4.6728

Max Act: 4.3981. Min Act: -0.1700

Data Index: 2175955 (Open Web Text)

Max Activating Token Index: 627