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

Dataset: Open Web Text

Neuron 1172 in Layer 4

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: 5.2489. Min Range: -5.2489

Max Act: 5.2489. Min Act: -0.1700

Data Index: 4534817 (Open Web Text)

Max Activating Token Index: 92

Text #1

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.1229. Min Act: -0.1700

Data Index: 1865608 (Open Web Text)

Max Activating Token Index: 360

Text #2

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0884. Min Act: -0.1700

Data Index: 2392958 (Open Web Text)

Max Activating Token Index: 239

Text #3

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0646. Min Act: -0.1700

Data Index: 1565657 (Open Web Text)

Max Activating Token Index: 341

Text #4

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0194. Min Act: -0.1700

Data Index: 880883 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0691. Min Act: -0.1700

Data Index: 3042886 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0122. Min Act: -0.1700

Data Index: 5655217 (Open Web Text)

Max Activating Token Index: 755

Text #7

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9983. Min Act: -0.1700

Data Index: 5788137 (Open Web Text)

Max Activating Token Index: 295

Text #8

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0275. Min Act: -0.1700

Data Index: 4893547 (Open Web Text)

Max Activating Token Index: 91

Text #9

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0194. Min Act: -0.1700

Data Index: 508125 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 5.2489. Min Range: -5.2489

Max Act: 5.0030. Min Act: -0.1700

Data Index: 7415770 (Open Web Text)

Max Activating Token Index: 942

Text #11

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9492. Min Act: -0.1700

Data Index: 7322375 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9577. Min Act: -0.1700

Data Index: 5412375 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9297. Min Act: -0.1700

Data Index: 5181405 (Open Web Text)

Max Activating Token Index: 787

Text #14

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9586. Min Act: -0.1700

Data Index: 4919323 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9360. Min Act: -0.1700

Data Index: 2359202 (Open Web Text)

Max Activating Token Index: 973

Text #16

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.8959. Min Act: -0.1700

Data Index: 1686389 (Open Web Text)

Max Activating Token Index: 519

Text #17

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9548. Min Act: -0.1700

Data Index: 7648451 (Open Web Text)

Max Activating Token Index: 779

Text #18

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9427. Min Act: -0.1700

Data Index: 4158747 (Open Web Text)

Max Activating Token Index: 635

Text #19

Max Range: 5.2489. Min Range: -5.2489

Max Act: 4.9512. Min Act: -0.1700

Data Index: 2005043 (Open Web Text)

Max Activating Token Index: 128