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

Dataset: Open Web Text

Neuron 2754 in Layer 6

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: 3.3130. Min Range: -3.3130

Max Act: 3.3130. Min Act: -0.1700

Data Index: 5934428 (Open Web Text)

Max Activating Token Index: 691

Text #1

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.2386. Min Act: -0.1700

Data Index: 4569044 (Open Web Text)

Max Activating Token Index: 688

Text #2

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1915. Min Act: -0.1700

Data Index: 6083869 (Open Web Text)

Max Activating Token Index: 900

Text #3

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1979. Min Act: -0.1700

Data Index: 6362283 (Open Web Text)

Max Activating Token Index: 838

Text #4

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1303. Min Act: -0.1700

Data Index: 5675318 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1371. Min Act: -0.1700

Data Index: 5555451 (Open Web Text)

Max Activating Token Index: 436

Text #6

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0998. Min Act: -0.1700

Data Index: 1208451 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1033. Min Act: -0.1700

Data Index: 7275233 (Open Web Text)

Max Activating Token Index: 239

Text #8

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1067. Min Act: -0.1700

Data Index: 591026 (Open Web Text)

Max Activating Token Index: 666

Text #9

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1089. Min Act: -0.1700

Data Index: 2651270 (Open Web Text)

Max Activating Token Index: 957

Text #10

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0679. Min Act: -0.1700

Data Index: 6185376 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0622. Min Act: -0.1700

Data Index: 6127273 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0614. Min Act: -0.1700

Data Index: 60823 (Open Web Text)

Max Activating Token Index: 46

Text #13

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0328. Min Act: -0.1700

Data Index: 2926776 (Open Web Text)

Max Activating Token Index: 416

Text #14

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0393. Min Act: -0.1700

Data Index: 5602243 (Open Web Text)

Max Activating Token Index: 702

Text #15

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0305. Min Act: -0.1700

Data Index: 5253010 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0061. Min Act: -0.1700

Data Index: 3260145 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0570. Min Act: -0.1700

Data Index: 2920428 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0355. Min Act: -0.1700

Data Index: 2484916 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0428. Min Act: -0.1700

Data Index: 4961326 (Open Web Text)

Max Activating Token Index: 439