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

Dataset: Open Web Text

Neuron 1370 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: 4.5409. Min Range: -4.5409

Max Act: 4.5409. Min Act: -0.1700

Data Index: 4502943 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.4286. Min Act: -0.1700

Data Index: 4928067 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.4047. Min Act: -0.1700

Data Index: 4383150 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3926. Min Act: -0.1700

Data Index: 2286262 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3672. Min Act: -0.1700

Data Index: 2469298 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3833. Min Act: -0.1700

Data Index: 1895145 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3368. Min Act: -0.1700

Data Index: 7783326 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3449. Min Act: -0.1700

Data Index: 3216051 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3259. Min Act: -0.1700

Data Index: 8497807 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3047. Min Act: -0.1700

Data Index: 3111270 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3134. Min Act: -0.1700

Data Index: 6886578 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.3335. Min Act: -0.1700

Data Index: 3484479 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2894. Min Act: -0.1700

Data Index: 8467016 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2715. Min Act: -0.1700

Data Index: 4839953 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2830. Min Act: -0.1700

Data Index: 6924047 (Open Web Text)

Max Activating Token Index: 22

Text #15

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2722. Min Act: -0.1700

Data Index: 5206208 (Open Web Text)

Max Activating Token Index: 13

Text #16

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2614. Min Act: -0.1700

Data Index: 1281493 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2522. Min Act: -0.1700

Data Index: 6967495 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2590. Min Act: -0.1700

Data Index: 3105329 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.5409. Min Range: -4.5409

Max Act: 4.2541. Min Act: -0.1700

Data Index: 6999806 (Open Web Text)

Max Activating Token Index: 3