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

Dataset: Open Web Text

Neuron 2922 in Layer 5

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: 4.1572. Min Range: -4.1572

Max Act: 4.1572. Min Act: -0.1700

Data Index: 6569744 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.1184. Min Act: -0.1700

Data Index: 1059886 (Open Web Text)

Max Activating Token Index: 391

Text #2

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0700. Min Act: -0.1700

Data Index: 3911653 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0420. Min Act: -0.1700

Data Index: 7620634 (Open Web Text)

Max Activating Token Index: 49

Text #4

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0552. Min Act: -0.1700

Data Index: 6403441 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0224. Min Act: -0.1700

Data Index: 8388773 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0031. Min Act: -0.1700

Data Index: 4359640 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 4.1572. Min Range: -4.1572

Max Act: 4.0158. Min Act: -0.1700

Data Index: 6110909 (Open Web Text)

Max Activating Token Index: 47

Text #8

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9735. Min Act: -0.1700

Data Index: 2292335 (Open Web Text)

Max Activating Token Index: 25

Text #9

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9533. Min Act: -0.1700

Data Index: 7441256 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9549. Min Act: -0.1700

Data Index: 561663 (Open Web Text)

Max Activating Token Index: 208

Text #11

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9302. Min Act: -0.1700

Data Index: 6007466 (Open Web Text)

Max Activating Token Index: 278

Text #12

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9055. Min Act: -0.1700

Data Index: 3839908 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9272. Min Act: -0.1700

Data Index: 5660062 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9089. Min Act: -0.1700

Data Index: 7495373 (Open Web Text)

Max Activating Token Index: 1001

Text #15

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9257. Min Act: -0.1700

Data Index: 8542327 (Open Web Text)

Max Activating Token Index: 55

Text #16

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9121. Min Act: -0.1700

Data Index: 2762041 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9053. Min Act: -0.1700

Data Index: 6308321 (Open Web Text)

Max Activating Token Index: 780

Text #18

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.9174. Min Act: -0.1700

Data Index: 2870458 (Open Web Text)

Max Activating Token Index: 24

Text #19

Max Range: 4.1572. Min Range: -4.1572

Max Act: 3.8896. Min Act: -0.1700

Data Index: 7267874 (Open Web Text)

Max Activating Token Index: 668