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

Dataset: Open Web Text

Neuron 1190 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: 3.9890. Min Range: -3.9890

Max Act: 3.9890. Min Act: -0.1700

Data Index: 1807886 (Open Web Text)

Max Activating Token Index: 515

Text #1

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.9388. Min Act: -0.1700

Data Index: 267419 (Open Web Text)

Max Activating Token Index: 115

Text #2

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.9344. Min Act: -0.1700

Data Index: 2482548 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.9430. Min Act: -0.1700

Data Index: 7909344 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.9176. Min Act: -0.1700

Data Index: 3443879 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.9057. Min Act: -0.1700

Data Index: 6697232 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8851. Min Act: -0.1700

Data Index: 2857624 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8569. Min Act: -0.1700

Data Index: 3056728 (Open Web Text)

Max Activating Token Index: 705

Text #8

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8835. Min Act: -0.1700

Data Index: 7905558 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8794. Min Act: -0.1700

Data Index: 8546117 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8568. Min Act: -0.1700

Data Index: 7887149 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8828. Min Act: -0.1700

Data Index: 4033500 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8748. Min Act: -0.1700

Data Index: 2001666 (Open Web Text)

Max Activating Token Index: 447

Text #13

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8726. Min Act: -0.1700

Data Index: 6895613 (Open Web Text)

Max Activating Token Index: 521

Text #14

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8508. Min Act: -0.1700

Data Index: 1161007 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8581. Min Act: -0.1700

Data Index: 3835553 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1206279 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8493. Min Act: -0.1700

Data Index: 349260 (Open Web Text)

Max Activating Token Index: 477

Text #18

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8622. Min Act: -0.1700

Data Index: 5062531 (Open Web Text)

Max Activating Token Index: 424

Text #19

Max Range: 3.9890. Min Range: -3.9890

Max Act: 3.8273. Min Act: -0.1700

Data Index: 6009136 (Open Web Text)

Max Activating Token Index: 213