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

Dataset: Open Web Text

Neuron 2593 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: 4.6697. Min Range: -4.6697

Max Act: 4.6697. Min Act: -0.1700

Data Index: 2480854 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.6449. Min Act: -0.1700

Data Index: 5042206 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.6022. Min Act: -0.1700

Data Index: 6330059 (Open Web Text)

Max Activating Token Index: 132

Text #3

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.6348. Min Act: -0.1700

Data Index: 3226401 (Open Web Text)

Max Activating Token Index: 720

Text #4

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.6004. Min Act: -0.1700

Data Index: 7546279 (Open Web Text)

Max Activating Token Index: 930

Text #5

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.6054. Min Act: -0.1700

Data Index: 3833700 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5946. Min Act: -0.1700

Data Index: 565907 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5760. Min Act: -0.1700

Data Index: 7932054 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5749. Min Act: -0.1700

Data Index: 2265853 (Open Web Text)

Max Activating Token Index: 678

Text #9

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5650. Min Act: -0.1700

Data Index: 4343420 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5505. Min Act: -0.1700

Data Index: 4493016 (Open Web Text)

Max Activating Token Index: 589

Text #11

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5546. Min Act: -0.1700

Data Index: 8660476 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5652. Min Act: -0.1700

Data Index: 2276236 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5400. Min Act: -0.1700

Data Index: 4109886 (Open Web Text)

Max Activating Token Index: 899

Text #14

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5422. Min Act: -0.1700

Data Index: 1230089 (Open Web Text)

Max Activating Token Index: 374

Text #15

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5520. Min Act: -0.1700

Data Index: 2919939 (Open Web Text)

Max Activating Token Index: 201

Text #16

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5528. Min Act: -0.1700

Data Index: 6169744 (Open Web Text)

Max Activating Token Index: 341

Text #17

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5600. Min Act: -0.1700

Data Index: 781120 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5568. Min Act: -0.1700

Data Index: 5789460 (Open Web Text)

Max Activating Token Index: 973

Text #19

Max Range: 4.6697. Min Range: -4.6697

Max Act: 4.5509. Min Act: -0.1700

Data Index: 4705565 (Open Web Text)

Max Activating Token Index: 127