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

Dataset: Open Web Text

Neuron 622 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: 4.6317. Min Range: -4.6317

Max Act: 4.6317. Min Act: -0.1700

Data Index: 5167019 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.6283. Min Act: -0.1700

Data Index: 7513753 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.5292. Min Act: -0.1700

Data Index: 4428068 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.5105. Min Act: -0.1700

Data Index: 48590 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.5154. Min Act: -0.1700

Data Index: 3047341 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.5133. Min Act: -0.1700

Data Index: 7125189 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.5052. Min Act: -0.1700

Data Index: 8381974 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4842. Min Act: -0.1700

Data Index: 4767036 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4999. Min Act: -0.1700

Data Index: 1736327 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4762. Min Act: -0.1700

Data Index: 5134320 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4453. Min Act: -0.1700

Data Index: 1142906 (Open Web Text)

Max Activating Token Index: 11

Text #11

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4496. Min Act: -0.1700

Data Index: 5678383 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4424. Min Act: -0.1700

Data Index: 5698873 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4680. Min Act: -0.1700

Data Index: 2723851 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4747. Min Act: -0.1700

Data Index: 1483868 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4645. Min Act: -0.1700

Data Index: 264196 (Open Web Text)

Max Activating Token Index: 15

Text #16

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4547. Min Act: -0.1700

Data Index: 7092465 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4527. Min Act: -0.1700

Data Index: 5829436 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4390. Min Act: -0.1700

Data Index: 1030630 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 4.6317. Min Range: -4.6317

Max Act: 4.4451. Min Act: -0.1700

Data Index: 4703505 (Open Web Text)

Max Activating Token Index: 7