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

Dataset: Open Web Text

Neuron 128 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: 4.5965. Min Range: -4.5965

Max Act: 4.5965. Min Act: -0.1700

Data Index: 1669131 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5606. Min Act: -0.1700

Data Index: 5380850 (Open Web Text)

Max Activating Token Index: 63

Text #2

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5751. Min Act: -0.1700

Data Index: 4033905 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5644. Min Act: -0.1700

Data Index: 5187195 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5080. Min Act: -0.1700

Data Index: 7316011 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5433. Min Act: -0.1700

Data Index: 2865613 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5166. Min Act: -0.1700

Data Index: 1669132 (Open Web Text)

Max Activating Token Index: 679

Text #7

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4898. Min Act: -0.1700

Data Index: 7316010 (Open Web Text)

Max Activating Token Index: 115

Text #8

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5219. Min Act: -0.1700

Data Index: 4191288 (Open Web Text)

Max Activating Token Index: 50

Text #9

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4719. Min Act: -0.1700

Data Index: 960702 (Open Web Text)

Max Activating Token Index: 570

Text #10

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4859. Min Act: -0.1700

Data Index: 4840030 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4558. Min Act: -0.1700

Data Index: 3221810 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4317. Min Act: -0.1700

Data Index: 3506979 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4430. Min Act: -0.1700

Data Index: 464135 (Open Web Text)

Max Activating Token Index: 34

Text #14

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4517. Min Act: -0.1700

Data Index: 7374344 (Open Web Text)

Max Activating Token Index: 162

Text #15

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4269. Min Act: -0.1700

Data Index: 2865614 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4069. Min Act: -0.1700

Data Index: 5666345 (Open Web Text)

Max Activating Token Index: 102

Text #17

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4069. Min Act: -0.1700

Data Index: 7217622 (Open Web Text)

Max Activating Token Index: 168

Text #18

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4022. Min Act: -0.1700

Data Index: 5187202 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4067. Min Act: -0.1700

Data Index: 7316004 (Open Web Text)

Max Activating Token Index: 266