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

Dataset: Open Web Text

Neuron 2237 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: 3.3854. Min Range: -3.3854

Max Act: 3.3854. Min Act: -0.1700

Data Index: 5390505 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.3126. Min Act: -0.1700

Data Index: 951695 (Open Web Text)

Max Activating Token Index: 514

Text #2

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2937. Min Act: -0.1700

Data Index: 7466236 (Open Web Text)

Max Activating Token Index: 596

Text #3

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2814. Min Act: -0.1700

Data Index: 5965615 (Open Web Text)

Max Activating Token Index: 82

Text #4

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2593. Min Act: -0.1700

Data Index: 2433897 (Open Web Text)

Max Activating Token Index: 440

Text #5

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2356. Min Act: -0.1700

Data Index: 7013489 (Open Web Text)

Max Activating Token Index: 907

Text #6

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2467. Min Act: -0.1700

Data Index: 889538 (Open Web Text)

Max Activating Token Index: 101

Text #7

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2485. Min Act: -0.1700

Data Index: 6053960 (Open Web Text)

Max Activating Token Index: 58

Text #8

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2229. Min Act: -0.1700

Data Index: 6940476 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2201. Min Act: -0.1700

Data Index: 7462553 (Open Web Text)

Max Activating Token Index: 513

Text #10

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2172. Min Act: -0.1700

Data Index: 4095998 (Open Web Text)

Max Activating Token Index: 894

Text #11

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2226. Min Act: -0.1700

Data Index: 1563143 (Open Web Text)

Max Activating Token Index: 736

Text #12

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1860. Min Act: -0.1700

Data Index: 3195111 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2097. Min Act: -0.1700

Data Index: 8654720 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.2108. Min Act: -0.1700

Data Index: 6628281 (Open Web Text)

Max Activating Token Index: 780

Text #15

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1858. Min Act: -0.1700

Data Index: 1729147 (Open Web Text)

Max Activating Token Index: 647

Text #16

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1965. Min Act: -0.1700

Data Index: 6712580 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1810. Min Act: -0.1700

Data Index: 2294465 (Open Web Text)

Max Activating Token Index: 404

Text #18

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1711. Min Act: -0.1700

Data Index: 2491969 (Open Web Text)

Max Activating Token Index: 709

Text #19

Max Range: 3.3854. Min Range: -3.3854

Max Act: 3.1836. Min Act: -0.1700

Data Index: 2407529 (Open Web Text)

Max Activating Token Index: 149