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

Dataset: Open Web Text

Neuron 1024 in Layer 5

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: 3.7455. Min Range: -3.7455

Max Act: 3.7455. Min Act: -0.1700

Data Index: 7637515 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.7114. Min Act: -0.1700

Data Index: 5223229 (Open Web Text)

Max Activating Token Index: 353

Text #2

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.7241. Min Act: -0.1700

Data Index: 6386358 (Open Web Text)

Max Activating Token Index: 798

Text #3

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6994. Min Act: -0.1700

Data Index: 4182733 (Open Web Text)

Max Activating Token Index: 958

Text #4

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6461. Min Act: -0.1700

Data Index: 5277900 (Open Web Text)

Max Activating Token Index: 818

Text #5

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6559. Min Act: -0.1700

Data Index: 5724072 (Open Web Text)

Max Activating Token Index: 554

Text #6

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6599. Min Act: -0.1700

Data Index: 6868748 (Open Web Text)

Max Activating Token Index: 710

Text #7

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6352. Min Act: -0.1700

Data Index: 2751149 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6121. Min Act: -0.1700

Data Index: 8767088 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6162. Min Act: -0.1700

Data Index: 2729926 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6186. Min Act: -0.1700

Data Index: 8809476 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5953. Min Act: -0.1700

Data Index: 1303036 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6203. Min Act: -0.1700

Data Index: 3986631 (Open Web Text)

Max Activating Token Index: 548

Text #13

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6093. Min Act: -0.1700

Data Index: 6347487 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6320. Min Act: -0.1700

Data Index: 4488871 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6241. Min Act: -0.1700

Data Index: 1839871 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5751. Min Act: -0.1700

Data Index: 6406562 (Open Web Text)

Max Activating Token Index: 805

Text #17

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5969. Min Act: -0.1700

Data Index: 8824040 (Open Web Text)

Max Activating Token Index: 464

Text #18

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.5785. Min Act: -0.1700

Data Index: 8410908 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 3.7455. Min Range: -3.7455

Max Act: 3.6051. Min Act: -0.1700

Data Index: 7252451 (Open Web Text)

Max Activating Token Index: 779