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

Dataset: Open Web Text

Neuron 2244 in Layer 2

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: 5.1867. Min Range: -5.1867

Max Act: 5.1867. Min Act: -0.1700

Data Index: 1067789 (Open Web Text)

Max Activating Token Index: 304

Text #1

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1510. Min Act: -0.1700

Data Index: 1802671 (Open Web Text)

Max Activating Token Index: 491

Text #2

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1866. Min Act: -0.1700

Data Index: 5162582 (Open Web Text)

Max Activating Token Index: 304

Text #3

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1520. Min Act: -0.1700

Data Index: 2365610 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1289. Min Act: -0.1700

Data Index: 750563 (Open Web Text)

Max Activating Token Index: 762

Text #5

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1332. Min Act: -0.1700

Data Index: 5375791 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1308. Min Act: -0.1700

Data Index: 4584841 (Open Web Text)

Max Activating Token Index: 398

Text #7

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1271. Min Act: -0.1700

Data Index: 575878 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1327. Min Act: -0.1700

Data Index: 8045333 (Open Web Text)

Max Activating Token Index: 507

Text #9

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1013. Min Act: -0.1700

Data Index: 7781492 (Open Web Text)

Max Activating Token Index: 304

Text #10

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1324. Min Act: -0.1700

Data Index: 37270 (Open Web Text)

Max Activating Token Index: 91

Text #11

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1106. Min Act: -0.1700

Data Index: 3322730 (Open Web Text)

Max Activating Token Index: 33

Text #12

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.0829. Min Act: -0.1700

Data Index: 1036335 (Open Web Text)

Max Activating Token Index: 866

Text #13

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1247. Min Act: -0.1700

Data Index: 5038105 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1017. Min Act: -0.1700

Data Index: 3157902 (Open Web Text)

Max Activating Token Index: 715

Text #15

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1037. Min Act: -0.1700

Data Index: 5358993 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.0978. Min Act: -0.1700

Data Index: 2663400 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1089. Min Act: -0.1700

Data Index: 1362245 (Open Web Text)

Max Activating Token Index: 490

Text #18

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1062. Min Act: -0.1700

Data Index: 5394941 (Open Web Text)

Max Activating Token Index: 781

Text #19

Max Range: 5.1867. Min Range: -5.1867

Max Act: 5.1466. Min Act: -0.1700

Data Index: 5507350 (Open Web Text)

Max Activating Token Index: 731