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

Dataset: Open Web Text

Neuron 495 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: 1.6245. Min Range: -1.6245

Max Act: 1.6245. Min Act: -0.1700

Data Index: 8152446 (Open Web Text)

Max Activating Token Index: 496

Text #1

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.6101. Min Act: -0.1700

Data Index: 7798505 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.6073. Min Act: -0.1700

Data Index: 5413084 (Open Web Text)

Max Activating Token Index: 525

Text #3

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5972. Min Act: -0.1700

Data Index: 7616130 (Open Web Text)

Max Activating Token Index: 381

Text #4

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5938. Min Act: -0.1700

Data Index: 3287969 (Open Web Text)

Max Activating Token Index: 602

Text #5

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5760. Min Act: -0.1700

Data Index: 6610623 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5594. Min Act: -0.1700

Data Index: 7068359 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5702. Min Act: -0.1699

Data Index: 636436 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5587. Min Act: -0.1700

Data Index: 8304052 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5542. Min Act: -0.1700

Data Index: 6156809 (Open Web Text)

Max Activating Token Index: 455

Text #10

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5619. Min Act: -0.1700

Data Index: 5617587 (Open Web Text)

Max Activating Token Index: 16

Text #11

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5420. Min Act: -0.1700

Data Index: 491938 (Open Web Text)

Max Activating Token Index: 737

Text #12

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5331. Min Act: -0.1700

Data Index: 2602330 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5267. Min Act: -0.1700

Data Index: 1917610 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5358. Min Act: -0.1700

Data Index: 421627 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5292. Min Act: -0.1700

Data Index: 7706312 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5323. Min Act: -0.1700

Data Index: 11393 (Open Web Text)

Max Activating Token Index: 352

Text #17

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5350. Min Act: -0.1700

Data Index: 776057 (Open Web Text)

Max Activating Token Index: 989

Text #18

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5363. Min Act: -0.1700

Data Index: 4849574 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 1.6245. Min Range: -1.6245

Max Act: 1.5350. Min Act: -0.1700

Data Index: 4834290 (Open Web Text)

Max Activating Token Index: 141