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

Dataset: Open Web Text

Neuron 1105 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: 3.7734. Min Range: -3.7734

Max Act: 3.7649. Min Act: -0.1700

Data Index: 4633656 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7734. Min Act: -0.1700

Data Index: 6570093 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7546. Min Act: -0.1700

Data Index: 3947454 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7501. Min Act: -0.1700

Data Index: 1035152 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7315. Min Act: -0.1700

Data Index: 1292076 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7244. Min Act: -0.1700

Data Index: 1675720 (Open Web Text)

Max Activating Token Index: 419

Text #6

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7382. Min Act: -0.1700

Data Index: 4409067 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7514. Min Act: -0.1700

Data Index: 8021465 (Open Web Text)

Max Activating Token Index: 121

Text #8

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7571. Min Act: -0.1700

Data Index: 8021132 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7511. Min Act: -0.1700

Data Index: 7832127 (Open Web Text)

Max Activating Token Index: 51

Text #10

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7282. Min Act: -0.1700

Data Index: 6962881 (Open Web Text)

Max Activating Token Index: 81

Text #11

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7285. Min Act: -0.1700

Data Index: 6588486 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7383. Min Act: -0.1700

Data Index: 6308572 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7378. Min Act: -0.1700

Data Index: 5027319 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7342. Min Act: -0.1700

Data Index: 3298842 (Open Web Text)

Max Activating Token Index: 208

Text #15

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7178. Min Act: -0.1700

Data Index: 1431681 (Open Web Text)

Max Activating Token Index: 245

Text #16

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7453. Min Act: -0.1700

Data Index: 2724545 (Open Web Text)

Max Activating Token Index: 431

Text #17

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.6978. Min Act: -0.1700

Data Index: 2545820 (Open Web Text)

Max Activating Token Index: 491

Text #18

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7146. Min Act: -0.1700

Data Index: 2705575 (Open Web Text)

Max Activating Token Index: 432

Text #19

Max Range: 3.7734. Min Range: -3.7734

Max Act: 3.7026. Min Act: -0.1700

Data Index: 992995 (Open Web Text)

Max Activating Token Index: 455