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

Dataset: Open Web Text

Neuron 2233 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: 1.7581. Min Range: -1.7581

Max Act: 1.7581. Min Act: -0.1695

Data Index: 1712130 (Open Web Text)

Max Activating Token Index: 787

Text #1

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6652. Min Act: -0.1700

Data Index: 7506761 (Open Web Text)

Max Activating Token Index: 563

Text #2

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6645. Min Act: -0.1700

Data Index: 5876243 (Open Web Text)

Max Activating Token Index: 282

Text #3

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6503. Min Act: -0.1700

Data Index: 5518261 (Open Web Text)

Max Activating Token Index: 388

Text #4

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6611. Min Act: -0.1700

Data Index: 8501967 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6481. Min Act: -0.1700

Data Index: 5612847 (Open Web Text)

Max Activating Token Index: 358

Text #6

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6359. Min Act: -0.1700

Data Index: 6052552 (Open Web Text)

Max Activating Token Index: 985

Text #7

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6346. Min Act: -0.1697

Data Index: 3651070 (Open Web Text)

Max Activating Token Index: 754

Text #8

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6405. Min Act: -0.1700

Data Index: 5032876 (Open Web Text)

Max Activating Token Index: 582

Text #9

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6208. Min Act: -0.1700

Data Index: 5660985 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6210. Min Act: -0.1700

Data Index: 5172611 (Open Web Text)

Max Activating Token Index: 226

Text #11

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6166. Min Act: -0.1700

Data Index: 1798098 (Open Web Text)

Max Activating Token Index: 105

Text #12

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6205. Min Act: -0.1700

Data Index: 5515539 (Open Web Text)

Max Activating Token Index: 831

Text #13

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6205. Min Act: -0.1700

Data Index: 8725648 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6203. Min Act: -0.1700

Data Index: 1388483 (Open Web Text)

Max Activating Token Index: 71

Text #15

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6189. Min Act: -0.1700

Data Index: 4662465 (Open Web Text)

Max Activating Token Index: 95

Text #16

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6069. Min Act: -0.1698

Data Index: 2825474 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6089. Min Act: -0.1700

Data Index: 6794762 (Open Web Text)

Max Activating Token Index: 605

Text #18

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6054. Min Act: -0.1700

Data Index: 4340412 (Open Web Text)

Max Activating Token Index: 857

Text #19

Max Range: 1.7581. Min Range: -1.7581

Max Act: 1.6135. Min Act: -0.1700

Data Index: 4811121 (Open Web Text)

Max Activating Token Index: 726