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

Dataset: Open Web Text

Neuron 1920 in Layer 1

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: 2.0030. Min Range: -2.0030

Max Act: 1.9971. Min Act: -0.1700

Data Index: 140094 (Open Web Text)

Max Activating Token Index: 886

Text #1

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9763. Min Act: -0.1700

Data Index: 470121 (Open Web Text)

Max Activating Token Index: 682

Text #2

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9839. Min Act: -0.1700

Data Index: 2139091 (Open Web Text)

Max Activating Token Index: 748

Text #3

Max Range: 2.0030. Min Range: -2.0030

Max Act: 2.0030. Min Act: -0.1700

Data Index: 8009954 (Open Web Text)

Max Activating Token Index: 749

Text #4

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9576. Min Act: -0.1700

Data Index: 1331109 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9560. Min Act: -0.1700

Data Index: 4648095 (Open Web Text)

Max Activating Token Index: 867

Text #6

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9515. Min Act: -0.1700

Data Index: 1927493 (Open Web Text)

Max Activating Token Index: 454

Text #7

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9543. Min Act: -0.1700

Data Index: 5749769 (Open Web Text)

Max Activating Token Index: 166

Text #8

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9516. Min Act: -0.1700

Data Index: 1276589 (Open Web Text)

Max Activating Token Index: 727

Text #9

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9625. Min Act: -0.1700

Data Index: 4685954 (Open Web Text)

Max Activating Token Index: 753

Text #10

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9380. Min Act: -0.1700

Data Index: 5150536 (Open Web Text)

Max Activating Token Index: 609

Text #11

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9529. Min Act: -0.1700

Data Index: 4056869 (Open Web Text)

Max Activating Token Index: 573

Text #12

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9446. Min Act: -0.1700

Data Index: 8588143 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9461. Min Act: -0.1700

Data Index: 4012594 (Open Web Text)

Max Activating Token Index: 991

Text #14

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9271. Min Act: -0.1700

Data Index: 4287457 (Open Web Text)

Max Activating Token Index: 218

Text #15

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9341. Min Act: -0.1700

Data Index: 4100043 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9148. Min Act: -0.1700

Data Index: 371933 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9199. Min Act: -0.1700

Data Index: 6694080 (Open Web Text)

Max Activating Token Index: 907

Text #18

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9427. Min Act: -0.1700

Data Index: 7588855 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 2.0030. Min Range: -2.0030

Max Act: 1.9253. Min Act: -0.1700

Data Index: 8686894 (Open Web Text)

Max Activating Token Index: 289