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

Dataset: Open Web Text

Neuron 2555 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: 1.8368. Min Range: -1.8368

Max Act: 1.8279. Min Act: -0.1700

Data Index: 2264964 (Open Web Text)

Max Activating Token Index: 20

Text #1

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.8368. Min Act: -0.1700

Data Index: 7593189 (Open Web Text)

Max Activating Token Index: 99

Text #2

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.8146. Min Act: -0.1700

Data Index: 4569338 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.8061. Min Act: -0.1700

Data Index: 7106322 (Open Web Text)

Max Activating Token Index: 467

Text #4

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.8088. Min Act: -0.1700

Data Index: 5898934 (Open Web Text)

Max Activating Token Index: 504

Text #5

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7965. Min Act: -0.1700

Data Index: 216279 (Open Web Text)

Max Activating Token Index: 353

Text #6

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7959. Min Act: -0.1700

Data Index: 809115 (Open Web Text)

Max Activating Token Index: 730

Text #7

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7820. Min Act: -0.1700

Data Index: 4459785 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7868. Min Act: -0.1700

Data Index: 569365 (Open Web Text)

Max Activating Token Index: 962

Text #9

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7751. Min Act: -0.1700

Data Index: 1310420 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7555. Min Act: -0.1700

Data Index: 7987560 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7772. Min Act: -0.1700

Data Index: 8578770 (Open Web Text)

Max Activating Token Index: 26

Text #12

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7812. Min Act: -0.1700

Data Index: 5251000 (Open Web Text)

Max Activating Token Index: 516

Text #13

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7655. Min Act: -0.1700

Data Index: 1053601 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7705. Min Act: -0.1700

Data Index: 2439224 (Open Web Text)

Max Activating Token Index: 493

Text #15

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7745. Min Act: -0.1700

Data Index: 421782 (Open Web Text)

Max Activating Token Index: 1008

Text #16

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7570. Min Act: -0.1700

Data Index: 1320859 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7722. Min Act: -0.1700

Data Index: 2382126 (Open Web Text)

Max Activating Token Index: 370

Text #18

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7698. Min Act: -0.1700

Data Index: 379305 (Open Web Text)

Max Activating Token Index: 670

Text #19

Max Range: 1.8368. Min Range: -1.8368

Max Act: 1.7561. Min Act: -0.1700

Data Index: 2149844 (Open Web Text)

Max Activating Token Index: 255