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

Dataset: Open Web Text

Neuron 387 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: 4.0821. Min Range: -4.0821

Max Act: 4.0821. Min Act: -0.1700

Data Index: 3742069 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0612. Min Act: -0.1700

Data Index: 3426230 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0597. Min Act: -0.1700

Data Index: 2320081 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0541. Min Act: -0.1700

Data Index: 4852302 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0365. Min Act: -0.1700

Data Index: 7658791 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0385. Min Act: -0.1700

Data Index: 238135 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0265. Min Act: -0.1700

Data Index: 7073193 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0005. Min Act: -0.1700

Data Index: 8685782 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0334. Min Act: -0.1700

Data Index: 439190 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9898. Min Act: -0.1700

Data Index: 8687645 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9996. Min Act: -0.1700

Data Index: 861703 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.0821. Min Range: -4.0821

Max Act: 4.0092. Min Act: -0.1700

Data Index: 2981084 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9974. Min Act: -0.1700

Data Index: 2655289 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9456. Min Act: -0.1700

Data Index: 5195977 (Open Web Text)

Max Activating Token Index: 874

Text #14

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9590. Min Act: -0.1700

Data Index: 5543305 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9486. Min Act: -0.1700

Data Index: 7515608 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9537. Min Act: -0.1700

Data Index: 1476489 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9581. Min Act: -0.1700

Data Index: 8135799 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9487. Min Act: -0.1700

Data Index: 4847781 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 4.0821. Min Range: -4.0821

Max Act: 3.9686. Min Act: -0.1700

Data Index: 4031367 (Open Web Text)

Max Activating Token Index: 314