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

Dataset: Open Web Text

Neuron 707 in Layer 0

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: 4.9354. Min Range: -4.9354

Max Act: 4.9354. Min Act: -0.1700

Data Index: 5842041 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.9014. Min Act: -0.1700

Data Index: 5841170 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8381. Min Act: -0.1700

Data Index: 3553688 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8574. Min Act: -0.1700

Data Index: 4676319 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8403. Min Act: -0.1700

Data Index: 26154 (Open Web Text)

Max Activating Token Index: 12

Text #5

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8331. Min Act: -0.1700

Data Index: 5131985 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8347. Min Act: -0.1700

Data Index: 1136095 (Open Web Text)

Max Activating Token Index: 861

Text #7

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8156. Min Act: -0.1700

Data Index: 2252815 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7967. Min Act: -0.1700

Data Index: 6453119 (Open Web Text)

Max Activating Token Index: 286

Text #9

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7847. Min Act: -0.1700

Data Index: 483304 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7767. Min Act: -0.1700

Data Index: 7544324 (Open Web Text)

Max Activating Token Index: 124

Text #11

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8064. Min Act: -0.1700

Data Index: 7151641 (Open Web Text)

Max Activating Token Index: 28

Text #12

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7899. Min Act: -0.1700

Data Index: 8666078 (Open Web Text)

Max Activating Token Index: 729

Text #13

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7825. Min Act: -0.1700

Data Index: 1775841 (Open Web Text)

Max Activating Token Index: 791

Text #14

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7395. Min Act: -0.1700

Data Index: 6687725 (Open Web Text)

Max Activating Token Index: 43

Text #15

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7605. Min Act: -0.1700

Data Index: 1628495 (Open Web Text)

Max Activating Token Index: 184

Text #16

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7495. Min Act: -0.1700

Data Index: 2245099 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7697. Min Act: -0.1700

Data Index: 5889116 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7752. Min Act: -0.1700

Data Index: 4816806 (Open Web Text)

Max Activating Token Index: 34

Text #19

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7632. Min Act: -0.1700

Data Index: 3201466 (Open Web Text)

Max Activating Token Index: 65