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

Dataset: Open Web Text

Neuron 714 in Layer 3

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: 5.0936. Min Range: -5.0936

Max Act: 5.0936. Min Act: -0.1700

Data Index: 3249532 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0454. Min Act: -0.1700

Data Index: 2239695 (Open Web Text)

Max Activating Token Index: 75

Text #2

Max Range: 5.0936. Min Range: -5.0936

Max Act: 5.0278. Min Act: -0.1700

Data Index: 5697046 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9677. Min Act: -0.1700

Data Index: 1609457 (Open Web Text)

Max Activating Token Index: 742

Text #4

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9842. Min Act: -0.1700

Data Index: 7884570 (Open Web Text)

Max Activating Token Index: 926

Text #5

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9522. Min Act: -0.1700

Data Index: 4678445 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9513. Min Act: -0.1700

Data Index: 1174879 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9465. Min Act: -0.1700

Data Index: 2503971 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9399. Min Act: -0.1700

Data Index: 7886048 (Open Web Text)

Max Activating Token Index: 572

Text #9

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9452. Min Act: -0.1700

Data Index: 4678444 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9132. Min Act: -0.1700

Data Index: 5887524 (Open Web Text)

Max Activating Token Index: 514

Text #11

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8991. Min Act: -0.1700

Data Index: 6214567 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8921. Min Act: -0.1700

Data Index: 1527401 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8557. Min Act: -0.1700

Data Index: 6304930 (Open Web Text)

Max Activating Token Index: 583

Text #14

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8825. Min Act: -0.1700

Data Index: 1344032 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9206. Min Act: -0.1700

Data Index: 1393302 (Open Web Text)

Max Activating Token Index: 984

Text #16

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.9047. Min Act: -0.1700

Data Index: 4903032 (Open Web Text)

Max Activating Token Index: 761

Text #17

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8515. Min Act: -0.1700

Data Index: 61543 (Open Web Text)

Max Activating Token Index: 492

Text #18

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8604. Min Act: -0.1700

Data Index: 2994610 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 5.0936. Min Range: -5.0936

Max Act: 4.8963. Min Act: -0.1700

Data Index: 3756347 (Open Web Text)

Max Activating Token Index: 746