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

Dataset: Open Web Text

Neuron 807 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: 2.8791. Min Range: -2.8791

Max Act: 2.8791. Min Act: -0.1700

Data Index: 8040402 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8200. Min Act: -0.1700

Data Index: 2082494 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8652. Min Act: -0.1700

Data Index: 2384501 (Open Web Text)

Max Activating Token Index: 398

Text #3

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8486. Min Act: -0.1700

Data Index: 1634913 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8236. Min Act: -0.1700

Data Index: 4417895 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8129. Min Act: -0.1700

Data Index: 6320191 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8182. Min Act: -0.1700

Data Index: 4528622 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7862. Min Act: -0.1700

Data Index: 1870388 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.6859. Min Act: -0.1700

Data Index: 5649473 (Open Web Text)

Max Activating Token Index: 547

Text #9

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8525. Min Act: -0.1700

Data Index: 717906 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7710. Min Act: -0.1700

Data Index: 3220611 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8360. Min Act: -0.1700

Data Index: 7526191 (Open Web Text)

Max Activating Token Index: 571

Text #12

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8039. Min Act: -0.1700

Data Index: 5405066 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.8054. Min Act: -0.1700

Data Index: 1959245 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7589. Min Act: -0.1700

Data Index: 8437853 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7517. Min Act: -0.1700

Data Index: 5570187 (Open Web Text)

Max Activating Token Index: 222

Text #16

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7593. Min Act: -0.1700

Data Index: 2802195 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7706. Min Act: -0.1700

Data Index: 6487623 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7633. Min Act: -0.1700

Data Index: 8219186 (Open Web Text)

Max Activating Token Index: 589

Text #19

Max Range: 2.8791. Min Range: -2.8791

Max Act: 2.7459. Min Act: -0.1700

Data Index: 1934466 (Open Web Text)

Max Activating Token Index: 4