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

Dataset: Open Web Text

Neuron 395 in Layer 3

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: 3.9637. Min Range: -3.9637

Max Act: 3.9467. Min Act: -0.1700

Data Index: 1229692 (Open Web Text)

Max Activating Token Index: 916

Text #1

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.9637. Min Act: -0.1700

Data Index: 476682 (Open Web Text)

Max Activating Token Index: 341

Text #2

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.9169. Min Act: -0.1700

Data Index: 654987 (Open Web Text)

Max Activating Token Index: 484

Text #3

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8760. Min Act: -0.1700

Data Index: 1592834 (Open Web Text)

Max Activating Token Index: 992

Text #4

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8634. Min Act: -0.1700

Data Index: 5543108 (Open Web Text)

Max Activating Token Index: 159

Text #5

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8865. Min Act: -0.1700

Data Index: 4404453 (Open Web Text)

Max Activating Token Index: 831

Text #6

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8625. Min Act: -0.1700

Data Index: 1617416 (Open Web Text)

Max Activating Token Index: 719

Text #7

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7739. Min Act: -0.1700

Data Index: 2370352 (Open Web Text)

Max Activating Token Index: 897

Text #8

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7453. Min Act: -0.1700

Data Index: 6520503 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7901. Min Act: -0.1700

Data Index: 7979791 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7150. Min Act: -0.1700

Data Index: 7427806 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.8115. Min Act: -0.1700

Data Index: 6532595 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7939. Min Act: -0.1700

Data Index: 3440991 (Open Web Text)

Max Activating Token Index: 484

Text #13

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7670. Min Act: -0.1700

Data Index: 2389482 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7137. Min Act: -0.1700

Data Index: 8190671 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7844. Min Act: -0.1700

Data Index: 83611 (Open Web Text)

Max Activating Token Index: 767

Text #16

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7159. Min Act: -0.1700

Data Index: 7268767 (Open Web Text)

Max Activating Token Index: 915

Text #17

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7489. Min Act: -0.1700

Data Index: 2987841 (Open Web Text)

Max Activating Token Index: 336

Text #18

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7239. Min Act: -0.1700

Data Index: 6237272 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 3.9637. Min Range: -3.9637

Max Act: 3.7656. Min Act: -0.1700

Data Index: 782114 (Open Web Text)

Max Activating Token Index: 803