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

Dataset: Open Web Text

Neuron 2319 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: 3.0834. Min Range: -3.0834

Max Act: 3.0834. Min Act: -0.1700

Data Index: 820843 (Open Web Text)

Max Activating Token Index: 523

Text #1

Max Range: 3.0834. Min Range: -3.0834

Max Act: 3.0126. Min Act: -0.1700

Data Index: 8028925 (Open Web Text)

Max Activating Token Index: 168

Text #2

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.9362. Min Act: -0.1700

Data Index: 6378255 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.9392. Min Act: -0.1700

Data Index: 7744150 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8978. Min Act: -0.1693

Data Index: 8679098 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8681. Min Act: -0.1700

Data Index: 6378248 (Open Web Text)

Max Activating Token Index: 231

Text #6

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8362. Min Act: -0.1700

Data Index: 818641 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8537. Min Act: -0.1700

Data Index: 7808604 (Open Web Text)

Max Activating Token Index: 788

Text #8

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8253. Min Act: -0.1700

Data Index: 8028927 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8433. Min Act: -0.1700

Data Index: 4115212 (Open Web Text)

Max Activating Token Index: 210

Text #10

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8496. Min Act: -0.1700

Data Index: 5328530 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8231. Min Act: -0.1700

Data Index: 1938518 (Open Web Text)

Max Activating Token Index: 63

Text #12

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8245. Min Act: -0.1700

Data Index: 4715998 (Open Web Text)

Max Activating Token Index: 319

Text #13

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8262. Min Act: -0.1700

Data Index: 8649365 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7994. Min Act: -0.1700

Data Index: 1183235 (Open Web Text)

Max Activating Token Index: 740

Text #15

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7904. Min Act: -0.1700

Data Index: 5918394 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7998. Min Act: -0.1699

Data Index: 8028931 (Open Web Text)

Max Activating Token Index: 219

Text #17

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.8013. Min Act: -0.1700

Data Index: 3868035 (Open Web Text)

Max Activating Token Index: 38

Text #18

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7939. Min Act: -0.1700

Data Index: 3125688 (Open Web Text)

Max Activating Token Index: 106

Text #19

Max Range: 3.0834. Min Range: -3.0834

Max Act: 2.7859. Min Act: -0.1700

Data Index: 3560475 (Open Web Text)

Max Activating Token Index: 744