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

Dataset: Open Web Text

Neuron 470 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: 4.1923. Min Range: -4.1923

Max Act: 4.1923. Min Act: -0.1700

Data Index: 4268057 (Open Web Text)

Max Activating Token Index: 311

Text #1

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.1340. Min Act: -0.1700

Data Index: 1487165 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0986. Min Act: -0.1700

Data Index: 2307160 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0439. Min Act: -0.1700

Data Index: 7035832 (Open Web Text)

Max Activating Token Index: 602

Text #4

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0718. Min Act: -0.1700

Data Index: 4281759 (Open Web Text)

Max Activating Token Index: 414

Text #5

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0713. Min Act: -0.1700

Data Index: 1786270 (Open Web Text)

Max Activating Token Index: 410

Text #6

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0320. Min Act: -0.1700

Data Index: 6488718 (Open Web Text)

Max Activating Token Index: 676

Text #7

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0670. Min Act: -0.1700

Data Index: 5352287 (Open Web Text)

Max Activating Token Index: 580

Text #8

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0099. Min Act: -0.1700

Data Index: 6213389 (Open Web Text)

Max Activating Token Index: 312

Text #9

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0705. Min Act: -0.1700

Data Index: 3279913 (Open Web Text)

Max Activating Token Index: 780

Text #10

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0017. Min Act: -0.1700

Data Index: 8123257 (Open Web Text)

Max Activating Token Index: 861

Text #11

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0349. Min Act: -0.1700

Data Index: 2470238 (Open Web Text)

Max Activating Token Index: 534

Text #12

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9668. Min Act: -0.1700

Data Index: 4303973 (Open Web Text)

Max Activating Token Index: 504

Text #13

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9893. Min Act: -0.1700

Data Index: 5760124 (Open Web Text)

Max Activating Token Index: 871

Text #14

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9946. Min Act: -0.1700

Data Index: 3988412 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9654. Min Act: -0.1700

Data Index: 6117338 (Open Web Text)

Max Activating Token Index: 516

Text #16

Max Range: 4.1923. Min Range: -4.1923

Max Act: 4.0067. Min Act: -0.1700

Data Index: 5644115 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9657. Min Act: -0.1700

Data Index: 3263718 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9744. Min Act: -0.1700

Data Index: 2544360 (Open Web Text)

Max Activating Token Index: 568

Text #19

Max Range: 4.1923. Min Range: -4.1923

Max Act: 3.9979. Min Act: -0.1700

Data Index: 4274805 (Open Web Text)

Max Activating Token Index: 284