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

Dataset: Open Web Text

Neuron 2840 in Layer 0

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: 3.5315. Min Range: -3.5315

Max Act: 3.5315. Min Act: -0.1700

Data Index: 8235681 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4877. Min Act: -0.1700

Data Index: 1938803 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4963. Min Act: -0.1700

Data Index: 4909717 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1658480 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4827. Min Act: -0.1700

Data Index: 4295543 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4768. Min Act: -0.1700

Data Index: 6521382 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4481. Min Act: -0.1700

Data Index: 1111433 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4326. Min Act: -0.1700

Data Index: 4256826 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4526. Min Act: -0.1700

Data Index: 6518196 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4281. Min Act: -0.1700

Data Index: 7747783 (Open Web Text)

Max Activating Token Index: 669

Text #10

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4250. Min Act: -0.1700

Data Index: 281096 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4055. Min Act: -0.1700

Data Index: 4363528 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4166. Min Act: -0.1700

Data Index: 7737092 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4265. Min Act: -0.1700

Data Index: 3373482 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4220. Min Act: -0.1700

Data Index: 1543095 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4064. Min Act: -0.1700

Data Index: 6274530 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4081. Min Act: -0.1700

Data Index: 5440887 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4050. Min Act: -0.1700

Data Index: 4819763 (Open Web Text)

Max Activating Token Index: 20

Text #18

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.4248. Min Act: -0.1700

Data Index: 4493350 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.5315. Min Range: -3.5315

Max Act: 3.3810. Min Act: -0.1700

Data Index: 553101 (Open Web Text)

Max Activating Token Index: 129