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

Dataset: Open Web Text

Neuron 799 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: 4.6004. Min Range: -4.6004

Max Act: 4.6004. Min Act: -0.1700

Data Index: 7858048 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5570. Min Act: -0.1700

Data Index: 6566693 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5427. Min Act: -0.1700

Data Index: 5383607 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5476. Min Act: -0.1700

Data Index: 3199168 (Open Web Text)

Max Activating Token Index: 309

Text #4

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5419. Min Act: -0.1700

Data Index: 3874295 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5191. Min Act: -0.1700

Data Index: 4133416 (Open Web Text)

Max Activating Token Index: 332

Text #6

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5092. Min Act: -0.1700

Data Index: 3261012 (Open Web Text)

Max Activating Token Index: 507

Text #7

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.5096. Min Act: -0.1700

Data Index: 5634927 (Open Web Text)

Max Activating Token Index: 278

Text #8

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4629. Min Act: -0.1700

Data Index: 5921000 (Open Web Text)

Max Activating Token Index: 206

Text #9

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4594. Min Act: -0.1700

Data Index: 597095 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4883. Min Act: -0.1700

Data Index: 2271883 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4797. Min Act: -0.1700

Data Index: 7485686 (Open Web Text)

Max Activating Token Index: 21

Text #12

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4404. Min Act: -0.1700

Data Index: 7998463 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4171. Min Act: -0.1700

Data Index: 2224955 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4325. Min Act: -0.1700

Data Index: 2857752 (Open Web Text)

Max Activating Token Index: 792

Text #15

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4437. Min Act: -0.1700

Data Index: 7575671 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4263. Min Act: -0.1700

Data Index: 2492656 (Open Web Text)

Max Activating Token Index: 262

Text #17

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4344. Min Act: -0.1700

Data Index: 7472129 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.4236. Min Act: -0.1700

Data Index: 3238249 (Open Web Text)

Max Activating Token Index: 352

Text #19

Max Range: 4.6004. Min Range: -4.6004

Max Act: 4.3978. Min Act: -0.1700

Data Index: 5345353 (Open Web Text)

Max Activating Token Index: 261