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

Dataset: Open Web Text

Neuron 1338 in Layer 5

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: 3.8860. Min Range: -3.8860

Max Act: 3.8860. Min Act: -0.1700

Data Index: 1790184 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.7461. Min Act: -0.1700

Data Index: 8229677 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.5285. Min Act: -0.1700

Data Index: 6372491 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3790. Min Act: -0.1700

Data Index: 4570202 (Open Web Text)

Max Activating Token Index: 778

Text #4

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3802. Min Act: -0.1700

Data Index: 3598322 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3528. Min Act: -0.1700

Data Index: 6061657 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3384. Min Act: -0.1700

Data Index: 8138223 (Open Web Text)

Max Activating Token Index: 614

Text #7

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3838. Min Act: -0.1700

Data Index: 6729578 (Open Web Text)

Max Activating Token Index: 32

Text #8

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3484. Min Act: -0.1700

Data Index: 3679064 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3265. Min Act: -0.1700

Data Index: 5032648 (Open Web Text)

Max Activating Token Index: 245

Text #10

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.3016. Min Act: -0.1700

Data Index: 7369795 (Open Web Text)

Max Activating Token Index: 202

Text #11

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2953. Min Act: -0.1700

Data Index: 1778626 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2624. Min Act: -0.1700

Data Index: 2457574 (Open Web Text)

Max Activating Token Index: 895

Text #13

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2298. Min Act: -0.1700

Data Index: 1273704 (Open Web Text)

Max Activating Token Index: 115

Text #14

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2537. Min Act: -0.1700

Data Index: 46248 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2317. Min Act: -0.1700

Data Index: 349068 (Open Web Text)

Max Activating Token Index: 112

Text #16

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.1798. Min Act: -0.1700

Data Index: 3339534 (Open Web Text)

Max Activating Token Index: 577

Text #17

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2022. Min Act: -0.1700

Data Index: 4258880 (Open Web Text)

Max Activating Token Index: 241

Text #18

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.1991. Min Act: -0.1700

Data Index: 6344234 (Open Web Text)

Max Activating Token Index: 810

Text #19

Max Range: 3.8860. Min Range: -3.8860

Max Act: 3.2244. Min Act: -0.1700

Data Index: 2671454 (Open Web Text)

Max Activating Token Index: 163