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

Dataset: Open Web Text

Neuron 1738 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: 4.0041. Min Range: -4.0041

Max Act: 4.0041. Min Act: -0.1700

Data Index: 4916154 (Open Web Text)

Max Activating Token Index: 628

Text #1

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.9242. Min Act: -0.1700

Data Index: 5715236 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.9080. Min Act: -0.1700

Data Index: 4988042 (Open Web Text)

Max Activating Token Index: 456

Text #3

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.8740. Min Act: -0.1700

Data Index: 32710 (Open Web Text)

Max Activating Token Index: 346

Text #4

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.8359. Min Act: -0.1700

Data Index: 1464910 (Open Web Text)

Max Activating Token Index: 214

Text #5

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7976. Min Act: -0.1700

Data Index: 2641339 (Open Web Text)

Max Activating Token Index: 556

Text #6

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.8002. Min Act: -0.1700

Data Index: 5349676 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7550. Min Act: -0.1700

Data Index: 5082487 (Open Web Text)

Max Activating Token Index: 410

Text #8

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7771. Min Act: -0.1700

Data Index: 2448523 (Open Web Text)

Max Activating Token Index: 124

Text #9

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7706. Min Act: -0.1700

Data Index: 2676926 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7992. Min Act: -0.1700

Data Index: 946891 (Open Web Text)

Max Activating Token Index: 190

Text #11

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7355. Min Act: -0.1700

Data Index: 50011 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7307. Min Act: -0.1700

Data Index: 8661271 (Open Web Text)

Max Activating Token Index: 769

Text #13

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7304. Min Act: -0.1700

Data Index: 1574848 (Open Web Text)

Max Activating Token Index: 817

Text #14

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7682. Min Act: -0.1700

Data Index: 4033828 (Open Web Text)

Max Activating Token Index: 800

Text #15

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7568. Min Act: -0.1700

Data Index: 6528391 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7490. Min Act: -0.1700

Data Index: 3597896 (Open Web Text)

Max Activating Token Index: 852

Text #17

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7042. Min Act: -0.1700

Data Index: 5212659 (Open Web Text)

Max Activating Token Index: 214

Text #18

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.7132. Min Act: -0.1700

Data Index: 2596061 (Open Web Text)

Max Activating Token Index: 521

Text #19

Max Range: 4.0041. Min Range: -4.0041

Max Act: 3.6986. Min Act: -0.1700

Data Index: 4447672 (Open Web Text)

Max Activating Token Index: 679