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

Dataset: Open Web Text

Neuron 626 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: 3.5811. Min Range: -3.5811

Max Act: 3.5645. Min Act: -0.1700

Data Index: 3843506 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5811. Min Act: -0.1700

Data Index: 6310092 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5125. Min Act: -0.1700

Data Index: 2666647 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5355. Min Act: -0.1700

Data Index: 335671 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4878. Min Act: -0.1700

Data Index: 7312779 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4844. Min Act: -0.1700

Data Index: 8294983 (Open Web Text)

Max Activating Token Index: 15

Text #6

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4820. Min Act: -0.1700

Data Index: 4275425 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.5016. Min Act: -0.1700

Data Index: 8157526 (Open Web Text)

Max Activating Token Index: 26

Text #8

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4531. Min Act: -0.1700

Data Index: 3355949 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4481. Min Act: -0.1700

Data Index: 5187847 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4387. Min Act: -0.1700

Data Index: 719923 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4688. Min Act: -0.1700

Data Index: 860391 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4168. Min Act: -0.1700

Data Index: 8266368 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4189. Min Act: -0.1700

Data Index: 7887584 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4299. Min Act: -0.1700

Data Index: 4291147 (Open Web Text)

Max Activating Token Index: 11

Text #15

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4112. Min Act: -0.1700

Data Index: 2947368 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4203. Min Act: -0.1700

Data Index: 8287886 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4471. Min Act: -0.1700

Data Index: 5703051 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4145. Min Act: -0.1700

Data Index: 341129 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.5811. Min Range: -3.5811

Max Act: 3.4124. Min Act: -0.1700

Data Index: 6297645 (Open Web Text)

Max Activating Token Index: 6