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

Dataset: Open Web Text

Neuron 2906 in Layer 1

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: 1.8703. Min Range: -1.8703

Max Act: 1.8642. Min Act: -0.1700

Data Index: 5135804 (Open Web Text)

Max Activating Token Index: 22

Text #1

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8703. Min Act: -0.1700

Data Index: 2505324 (Open Web Text)

Max Activating Token Index: 355

Text #2

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8612. Min Act: -0.1700

Data Index: 3909801 (Open Web Text)

Max Activating Token Index: 603

Text #3

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8569. Min Act: -0.1700

Data Index: 6991385 (Open Web Text)

Max Activating Token Index: 504

Text #4

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8509. Min Act: -0.1700

Data Index: 7350450 (Open Web Text)

Max Activating Token Index: 190

Text #5

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8493. Min Act: -0.1700

Data Index: 6026625 (Open Web Text)

Max Activating Token Index: 530

Text #6

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8385. Min Act: -0.1700

Data Index: 7817475 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8407. Min Act: -0.1700

Data Index: 3992667 (Open Web Text)

Max Activating Token Index: 259

Text #8

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8377. Min Act: -0.1700

Data Index: 5484407 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8407. Min Act: -0.1700

Data Index: 2368091 (Open Web Text)

Max Activating Token Index: 706

Text #10

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8373. Min Act: -0.1700

Data Index: 1604260 (Open Web Text)

Max Activating Token Index: 357

Text #11

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8357. Min Act: -0.1700

Data Index: 7357120 (Open Web Text)

Max Activating Token Index: 148

Text #12

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8257. Min Act: -0.1700

Data Index: 5856131 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8208. Min Act: -0.1700

Data Index: 3369237 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8242. Min Act: -0.1700

Data Index: 6290499 (Open Web Text)

Max Activating Token Index: 146

Text #15

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8236. Min Act: -0.1700

Data Index: 901033 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8195. Min Act: -0.1696

Data Index: 4636016 (Open Web Text)

Max Activating Token Index: 297

Text #17

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8175. Min Act: -0.1700

Data Index: 434516 (Open Web Text)

Max Activating Token Index: 262

Text #18

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8178. Min Act: -0.1696

Data Index: 3681660 (Open Web Text)

Max Activating Token Index: 45

Text #19

Max Range: 1.8703. Min Range: -1.8703

Max Act: 1.8166. Min Act: -0.1700

Data Index: 7382957 (Open Web Text)

Max Activating Token Index: 432