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

Dataset: Open Web Text

Neuron 2464 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: 3.4186. Min Range: -3.4186

Max Act: 3.4027. Min Act: -0.1700

Data Index: 8517445 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.4186. Min Act: -0.1700

Data Index: 5527921 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.3065. Min Act: -0.1700

Data Index: 1185427 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2727. Min Act: -0.1700

Data Index: 8045366 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.3020. Min Act: -0.1700

Data Index: 4613375 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 1890283 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 7506666 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 6501823 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 6429004 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 1444495 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 8525616 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 8097984 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2871. Min Act: -0.1700

Data Index: 2581931 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2672. Min Act: -0.1700

Data Index: 6251230 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2525. Min Act: -0.1700

Data Index: 757599 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2615. Min Act: -0.1700

Data Index: 7795146 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2235. Min Act: -0.1700

Data Index: 1154317 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2176. Min Act: -0.1700

Data Index: 6601690 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2124. Min Act: -0.1700

Data Index: 4486174 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.4186. Min Range: -3.4186

Max Act: 3.2344. Min Act: -0.1700

Data Index: 2141834 (Open Web Text)

Max Activating Token Index: 5