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

Dataset: Open Web Text

Neuron 899 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: 3.7102. Min Range: -3.7102

Max Act: 3.7102. Min Act: -0.1700

Data Index: 6459450 (Open Web Text)

Max Activating Token Index: 387

Text #1

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.6384. Min Act: -0.1700

Data Index: 3016869 (Open Web Text)

Max Activating Token Index: 213

Text #2

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5796. Min Act: -0.1700

Data Index: 8751466 (Open Web Text)

Max Activating Token Index: 550

Text #3

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5763. Min Act: -0.1700

Data Index: 511043 (Open Web Text)

Max Activating Token Index: 897

Text #4

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5631. Min Act: -0.1700

Data Index: 3705205 (Open Web Text)

Max Activating Token Index: 518

Text #5

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5468. Min Act: -0.1700

Data Index: 6287215 (Open Web Text)

Max Activating Token Index: 351

Text #6

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5504. Min Act: -0.1700

Data Index: 3016870 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5378. Min Act: -0.1700

Data Index: 151894 (Open Web Text)

Max Activating Token Index: 340

Text #8

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5246. Min Act: -0.1700

Data Index: 6432144 (Open Web Text)

Max Activating Token Index: 318

Text #9

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5220. Min Act: -0.1700

Data Index: 1543175 (Open Web Text)

Max Activating Token Index: 250

Text #10

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5267. Min Act: -0.1700

Data Index: 3279631 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5046. Min Act: -0.1700

Data Index: 5679032 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5108. Min Act: -0.1700

Data Index: 786897 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5068. Min Act: -0.1700

Data Index: 5346179 (Open Web Text)

Max Activating Token Index: 931

Text #14

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.5029. Min Act: -0.1700

Data Index: 5047187 (Open Web Text)

Max Activating Token Index: 660

Text #15

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.4932. Min Act: -0.1700

Data Index: 4524533 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.4838. Min Act: -0.1700

Data Index: 3579676 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.4868. Min Act: -0.1700

Data Index: 3854603 (Open Web Text)

Max Activating Token Index: 820

Text #18

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.4880. Min Act: -0.1700

Data Index: 3860944 (Open Web Text)

Max Activating Token Index: 488

Text #19

Max Range: 3.7102. Min Range: -3.7102

Max Act: 3.4803. Min Act: -0.1700

Data Index: 5152112 (Open Web Text)

Max Activating Token Index: 907