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

Dataset: Open Web Text

Neuron 503 in Layer 4

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: 1.6402. Min Range: -1.6402

Max Act: 1.6204. Min Act: -0.1700

Data Index: 2747123 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.6402. Min Act: -0.1700

Data Index: 242666 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.5808. Min Act: -0.1700

Data Index: 4694512 (Open Web Text)

Max Activating Token Index: 184

Text #3

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.6024. Min Act: -0.1700

Data Index: 6971612 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.5871. Min Act: -0.1700

Data Index: 3038769 (Open Web Text)

Max Activating Token Index: 294

Text #5

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.5266. Min Act: -0.1700

Data Index: 4858098 (Open Web Text)

Max Activating Token Index: 375

Text #6

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4999. Min Act: -0.1700

Data Index: 5118129 (Open Web Text)

Max Activating Token Index: 610

Text #7

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4847. Min Act: -0.1700

Data Index: 8366922 (Open Web Text)

Max Activating Token Index: 272

Text #8

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4675. Min Act: -0.1700

Data Index: 7443533 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4480. Min Act: -0.1700

Data Index: 1771228 (Open Web Text)

Max Activating Token Index: 357

Text #10

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4545. Min Act: -0.1700

Data Index: 6689346 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4590. Min Act: -0.1700

Data Index: 6452064 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4644. Min Act: -0.1700

Data Index: 3424062 (Open Web Text)

Max Activating Token Index: 273

Text #13

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4478. Min Act: -0.1700

Data Index: 7566849 (Open Web Text)

Max Activating Token Index: 287

Text #14

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4589. Min Act: -0.1700

Data Index: 2451714 (Open Web Text)

Max Activating Token Index: 327

Text #15

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4348. Min Act: -0.1700

Data Index: 5007615 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4654. Min Act: -0.1700

Data Index: 293483 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4658. Min Act: -0.1700

Data Index: 3765535 (Open Web Text)

Max Activating Token Index: 421

Text #18

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4474. Min Act: -0.1700

Data Index: 1673854 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4279. Min Act: -0.1700

Data Index: 3918976 (Open Web Text)

Max Activating Token Index: 523