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

Dataset: Open Web Text

Neuron 1651 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: 5.2132. Min Range: -5.2132

Max Act: 5.2132. Min Act: -0.1700

Data Index: 3900574 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.1035. Min Act: -0.1700

Data Index: 3703032 (Open Web Text)

Max Activating Token Index: 10

Text #2

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0554. Min Act: -0.1700

Data Index: 677470 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0466. Min Act: -0.1700

Data Index: 3538772 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0367. Min Act: -0.1700

Data Index: 7745671 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0315. Min Act: -0.1700

Data Index: 2381586 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1416303 (Open Web Text)

Max Activating Token Index: 17

Text #7

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0543. Min Act: -0.1700

Data Index: 8512540 (Open Web Text)

Max Activating Token Index: 9

Text #8

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0373. Min Act: -0.1700

Data Index: 4448389 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0117. Min Act: -0.1700

Data Index: 5453670 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 5.2132. Min Range: -5.2132

Max Act: 5.0104. Min Act: -0.1700

Data Index: 5108955 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9801. Min Act: -0.1700

Data Index: 8716683 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9652. Min Act: -0.1700

Data Index: 7963268 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9725. Min Act: -0.1700

Data Index: 3601069 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9311. Min Act: -0.1700

Data Index: 2227732 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9406. Min Act: -0.1700

Data Index: 4061867 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9560. Min Act: -0.1700

Data Index: 8075959 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9433. Min Act: -0.1700

Data Index: 5578179 (Open Web Text)

Max Activating Token Index: 12

Text #18

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9412. Min Act: -0.1700

Data Index: 1739672 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 5.2132. Min Range: -5.2132

Max Act: 4.9607. Min Act: -0.1700

Data Index: 245455 (Open Web Text)

Max Activating Token Index: 5