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

Dataset: Open Web Text

Neuron 1840 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: 2.5395. Min Range: -2.5395

Max Act: 2.5382. Min Act: -0.1700

Data Index: 2212587 (Open Web Text)

Max Activating Token Index: 558

Text #1

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.5395. Min Act: -0.1700

Data Index: 624659 (Open Web Text)

Max Activating Token Index: 151

Text #2

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.5311. Min Act: -0.1700

Data Index: 2342432 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.5044. Min Act: -0.1700

Data Index: 1754191 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4920. Min Act: -0.1700

Data Index: 3472537 (Open Web Text)

Max Activating Token Index: 303

Text #5

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4794. Min Act: -0.1700

Data Index: 6970168 (Open Web Text)

Max Activating Token Index: 495

Text #6

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4760. Min Act: -0.1700

Data Index: 6619286 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4680. Min Act: -0.1700

Data Index: 2945852 (Open Web Text)

Max Activating Token Index: 345

Text #8

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4608. Min Act: -0.1700

Data Index: 1235959 (Open Web Text)

Max Activating Token Index: 848

Text #9

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4516. Min Act: -0.1700

Data Index: 5626861 (Open Web Text)

Max Activating Token Index: 441

Text #10

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4352. Min Act: -0.1700

Data Index: 4491881 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4478. Min Act: -0.1700

Data Index: 287356 (Open Web Text)

Max Activating Token Index: 361

Text #12

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4449. Min Act: -0.1700

Data Index: 7535222 (Open Web Text)

Max Activating Token Index: 1002

Text #13

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4580. Min Act: -0.1700

Data Index: 8235411 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4423. Min Act: -0.1700

Data Index: 8130311 (Open Web Text)

Max Activating Token Index: 325

Text #15

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4258. Min Act: -0.1700

Data Index: 7923602 (Open Web Text)

Max Activating Token Index: 146

Text #16

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4149. Min Act: -0.1700

Data Index: 4561226 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4317. Min Act: -0.1700

Data Index: 99389 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4206. Min Act: -0.1700

Data Index: 1099293 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 2.5395. Min Range: -2.5395

Max Act: 2.4217. Min Act: -0.1700

Data Index: 6316357 (Open Web Text)

Max Activating Token Index: 587