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

Dataset: Open Web Text

Neuron 2676 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: 3.1518. Min Range: -3.1518

Max Act: 3.1518. Min Act: -0.1700

Data Index: 5215865 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1383. Min Act: -0.1700

Data Index: 6562019 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1331. Min Act: -0.1700

Data Index: 7382033 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1298. Min Act: -0.1700

Data Index: 6972186 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1318. Min Act: -0.1700

Data Index: 7432655 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1019. Min Act: -0.1700

Data Index: 7262035 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1044. Min Act: -0.1700

Data Index: 3943076 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1132. Min Act: -0.1700

Data Index: 8199322 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.1092. Min Act: -0.1700

Data Index: 7485297 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0925. Min Act: -0.1700

Data Index: 7934734 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0856. Min Act: -0.1700

Data Index: 2371342 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0856. Min Act: -0.1700

Data Index: 2853005 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0903. Min Act: -0.1700

Data Index: 2845251 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0991. Min Act: -0.1700

Data Index: 5475602 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0917. Min Act: -0.1700

Data Index: 8260930 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0917. Min Act: -0.1700

Data Index: 1855810 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0998. Min Act: -0.1700

Data Index: 5458257 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0763. Min Act: -0.1700

Data Index: 2248085 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0693. Min Act: -0.1700

Data Index: 6759670 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1518. Min Range: -3.1518

Max Act: 3.0674. Min Act: -0.1700

Data Index: 7896304 (Open Web Text)

Max Activating Token Index: 6