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

Dataset: Open Web Text

Neuron 2137 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: 4.4774. Min Range: -4.4774

Max Act: 4.4774. Min Act: -0.1700

Data Index: 5524334 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4497. Min Act: -0.1700

Data Index: 1230466 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4611. Min Act: -0.1700

Data Index: 2269662 (Open Web Text)

Max Activating Token Index: 790

Text #3

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4535. Min Act: -0.1700

Data Index: 760392 (Open Web Text)

Max Activating Token Index: 1019

Text #4

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4685. Min Act: -0.1700

Data Index: 3914745 (Open Web Text)

Max Activating Token Index: 1018

Text #5

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4291. Min Act: -0.1700

Data Index: 136383 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4279. Min Act: -0.1700

Data Index: 8589028 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4153. Min Act: -0.1700

Data Index: 514930 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4312. Min Act: -0.1700

Data Index: 3681665 (Open Web Text)

Max Activating Token Index: 797

Text #9

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3998. Min Act: -0.1700

Data Index: 3565960 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4170. Min Act: -0.1700

Data Index: 7900097 (Open Web Text)

Max Activating Token Index: 686

Text #11

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4374. Min Act: -0.1700

Data Index: 3565959 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4569. Min Act: -0.1700

Data Index: 1506487 (Open Web Text)

Max Activating Token Index: 555

Text #13

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3934. Min Act: -0.1700

Data Index: 514934 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3944. Min Act: -0.1700

Data Index: 2404165 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3908. Min Act: -0.1700

Data Index: 4207050 (Open Web Text)

Max Activating Token Index: 836

Text #16

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3955. Min Act: -0.1700

Data Index: 4207681 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4000. Min Act: -0.1700

Data Index: 5755876 (Open Web Text)

Max Activating Token Index: 1000

Text #18

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.4112. Min Act: -0.1700

Data Index: 5841076 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 4.4774. Min Range: -4.4774

Max Act: 4.3864. Min Act: -0.1700

Data Index: 6008692 (Open Web Text)

Max Activating Token Index: 653