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

Dataset: Open Web Text

Neuron 1881 in Layer 2

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: 5.8709. Min Range: -5.8709

Max Act: 5.8709. Min Act: -0.1700

Data Index: 5042926 (Open Web Text)

Max Activating Token Index: 729

Text #1

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.5497. Min Act: -0.1700

Data Index: 6462147 (Open Web Text)

Max Activating Token Index: 751

Text #2

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4918. Min Act: -0.1700

Data Index: 7715238 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4772. Min Act: -0.1700

Data Index: 5446523 (Open Web Text)

Max Activating Token Index: 77

Text #4

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4483. Min Act: -0.1700

Data Index: 4264583 (Open Web Text)

Max Activating Token Index: 914

Text #5

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4194. Min Act: -0.1700

Data Index: 4924057 (Open Web Text)

Max Activating Token Index: 902

Text #6

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4067. Min Act: -0.1700

Data Index: 5803652 (Open Web Text)

Max Activating Token Index: 86

Text #7

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.3614. Min Act: -0.1700

Data Index: 594274 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.3919. Min Act: -0.1700

Data Index: 2331892 (Open Web Text)

Max Activating Token Index: 787

Text #9

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.4146. Min Act: -0.1700

Data Index: 6026467 (Open Web Text)

Max Activating Token Index: 739

Text #10

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.3262. Min Act: -0.1700

Data Index: 5414049 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.3485. Min Act: -0.1700

Data Index: 5261881 (Open Web Text)

Max Activating Token Index: 244

Text #12

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.3578. Min Act: -0.1700

Data Index: 1644969 (Open Web Text)

Max Activating Token Index: 603

Text #13

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2939. Min Act: -0.1700

Data Index: 5975744 (Open Web Text)

Max Activating Token Index: 741

Text #14

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2594. Min Act: -0.1700

Data Index: 2108500 (Open Web Text)

Max Activating Token Index: 417

Text #15

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2355. Min Act: -0.1700

Data Index: 5380843 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2038. Min Act: -0.1700

Data Index: 5908489 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2207. Min Act: -0.1700

Data Index: 1612015 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2411. Min Act: -0.1700

Data Index: 6394590 (Open Web Text)

Max Activating Token Index: 981

Text #19

Max Range: 5.8709. Min Range: -5.8709

Max Act: 5.2354. Min Act: -0.1700

Data Index: 2765403 (Open Web Text)

Max Activating Token Index: 138