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

Dataset: Open Web Text

Neuron 1620 in Layer 0

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: 4.3064. Min Range: -4.3064

Max Act: 4.3064. Min Act: -0.1700

Data Index: 8479377 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2668. Min Act: -0.1700

Data Index: 5044770 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2875. Min Act: -0.1700

Data Index: 6740175 (Open Web Text)

Max Activating Token Index: 709

Text #3

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2362. Min Act: -0.1700

Data Index: 747720 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2629. Min Act: -0.1700

Data Index: 6904226 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2237. Min Act: -0.1700

Data Index: 5615320 (Open Web Text)

Max Activating Token Index: 357

Text #6

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.2011. Min Act: -0.1700

Data Index: 621553 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1777. Min Act: -0.1700

Data Index: 289824 (Open Web Text)

Max Activating Token Index: 28

Text #8

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1867. Min Act: -0.1700

Data Index: 6043562 (Open Web Text)

Max Activating Token Index: 100

Text #9

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1740. Min Act: -0.1700

Data Index: 6216885 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1642. Min Act: -0.1700

Data Index: 4506838 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1856. Min Act: -0.1700

Data Index: 3297504 (Open Web Text)

Max Activating Token Index: 30

Text #12

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1445. Min Act: -0.1700

Data Index: 5152432 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1447. Min Act: -0.1700

Data Index: 1650071 (Open Web Text)

Max Activating Token Index: 857

Text #14

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1592. Min Act: -0.1700

Data Index: 5993930 (Open Web Text)

Max Activating Token Index: 50

Text #15

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1632. Min Act: -0.1700

Data Index: 5987505 (Open Web Text)

Max Activating Token Index: 322

Text #16

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1361. Min Act: -0.1700

Data Index: 8240621 (Open Web Text)

Max Activating Token Index: 292

Text #17

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1545. Min Act: -0.1700

Data Index: 4228938 (Open Web Text)

Max Activating Token Index: 776

Text #18

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1359. Min Act: -0.1700

Data Index: 7627924 (Open Web Text)

Max Activating Token Index: 859

Text #19

Max Range: 4.3064. Min Range: -4.3064

Max Act: 4.1385. Min Act: -0.1700

Data Index: 7073679 (Open Web Text)

Max Activating Token Index: 683