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

Dataset: Open Web Text

Neuron 1595 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: 4.0550. Min Range: -4.0550

Max Act: 4.0550. Min Act: -0.1700

Data Index: 7133671 (Open Web Text)

Max Activating Token Index: 623

Text #1

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.9806. Min Act: -0.1700

Data Index: 7291599 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8498. Min Act: -0.1700

Data Index: 3893114 (Open Web Text)

Max Activating Token Index: 589

Text #3

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8786. Min Act: -0.1700

Data Index: 2110842 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8198. Min Act: -0.1700

Data Index: 6889766 (Open Web Text)

Max Activating Token Index: 765

Text #5

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8582. Min Act: -0.1700

Data Index: 6587751 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8815. Min Act: -0.1700

Data Index: 8637189 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8200. Min Act: -0.1700

Data Index: 505191 (Open Web Text)

Max Activating Token Index: 534

Text #8

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8365. Min Act: -0.1700

Data Index: 7230950 (Open Web Text)

Max Activating Token Index: 878

Text #9

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8224. Min Act: -0.1700

Data Index: 618544 (Open Web Text)

Max Activating Token Index: 157

Text #10

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.7888. Min Act: -0.1700

Data Index: 8529168 (Open Web Text)

Max Activating Token Index: 780

Text #11

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8109. Min Act: -0.1700

Data Index: 3170085 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8146. Min Act: -0.1700

Data Index: 1016175 (Open Web Text)

Max Activating Token Index: 170

Text #13

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8065. Min Act: -0.1700

Data Index: 3200387 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8059. Min Act: -0.1700

Data Index: 3783609 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.7966. Min Act: -0.1700

Data Index: 3892937 (Open Web Text)

Max Activating Token Index: 546

Text #16

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.8112. Min Act: -0.1700

Data Index: 2667205 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.7998. Min Act: -0.1700

Data Index: 6924334 (Open Web Text)

Max Activating Token Index: 202

Text #18

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.7981. Min Act: -0.1700

Data Index: 2104017 (Open Web Text)

Max Activating Token Index: 565

Text #19

Max Range: 4.0550. Min Range: -4.0550

Max Act: 3.7750. Min Act: -0.1700

Data Index: 7107667 (Open Web Text)

Max Activating Token Index: 189