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

Dataset: Open Web Text

Neuron 1916 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: 3.4570. Min Range: -3.4570

Max Act: 3.4570. Min Act: -0.1700

Data Index: 989443 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.4547. Min Act: -0.1700

Data Index: 481228 (Open Web Text)

Max Activating Token Index: 722

Text #2

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3927. Min Act: -0.1700

Data Index: 5141581 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3860. Min Act: -0.1700

Data Index: 8808607 (Open Web Text)

Max Activating Token Index: 729

Text #4

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3924. Min Act: -0.1700

Data Index: 7988145 (Open Web Text)

Max Activating Token Index: 997

Text #5

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3675. Min Act: -0.1700

Data Index: 6373449 (Open Web Text)

Max Activating Token Index: 273

Text #6

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.3259. Min Act: -0.1700

Data Index: 3280085 (Open Web Text)

Max Activating Token Index: 848

Text #7

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2960. Min Act: -0.1700

Data Index: 1865274 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2817. Min Act: -0.1700

Data Index: 8803332 (Open Web Text)

Max Activating Token Index: 86

Text #9

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2981. Min Act: -0.1700

Data Index: 5756506 (Open Web Text)

Max Activating Token Index: 115

Text #10

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2903. Min Act: -0.1700

Data Index: 2085720 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2611. Min Act: -0.1700

Data Index: 3209710 (Open Web Text)

Max Activating Token Index: 297

Text #12

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2769. Min Act: -0.1700

Data Index: 7092535 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2657. Min Act: -0.1700

Data Index: 7152680 (Open Web Text)

Max Activating Token Index: 920

Text #14

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2414. Min Act: -0.1700

Data Index: 5750849 (Open Web Text)

Max Activating Token Index: 655

Text #15

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2210. Min Act: -0.1700

Data Index: 7349880 (Open Web Text)

Max Activating Token Index: 333

Text #16

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.1974. Min Act: -0.1700

Data Index: 2885689 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.2011. Min Act: -0.1700

Data Index: 4101537 (Open Web Text)

Max Activating Token Index: 257

Text #18

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.1999. Min Act: -0.1700

Data Index: 5811755 (Open Web Text)

Max Activating Token Index: 792

Text #19

Max Range: 3.4570. Min Range: -3.4570

Max Act: 3.1944. Min Act: -0.1700

Data Index: 2780494 (Open Web Text)

Max Activating Token Index: 577