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

Dataset: Open Web Text

Neuron 1768 in Layer 3

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: 4.2732. Min Range: -4.2732

Max Act: 4.2732. Min Act: -0.1700

Data Index: 6848604 (Open Web Text)

Max Activating Token Index: 36

Text #1

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2593. Min Act: -0.1700

Data Index: 2559848 (Open Web Text)

Max Activating Token Index: 17

Text #2

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2539. Min Act: -0.1700

Data Index: 2383164 (Open Web Text)

Max Activating Token Index: 31

Text #3

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2407. Min Act: -0.1700

Data Index: 1512064 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2440. Min Act: -0.1700

Data Index: 1403612 (Open Web Text)

Max Activating Token Index: 370

Text #5

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2372. Min Act: -0.1700

Data Index: 5947245 (Open Web Text)

Max Activating Token Index: 324

Text #6

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.2052. Min Act: -0.1700

Data Index: 256747 (Open Web Text)

Max Activating Token Index: 31

Text #7

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1949. Min Act: -0.1700

Data Index: 8566742 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1865. Min Act: -0.1700

Data Index: 4069553 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1863. Min Act: -0.1700

Data Index: 5358715 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1869. Min Act: -0.1700

Data Index: 2189179 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1983. Min Act: -0.1700

Data Index: 7022791 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1330. Min Act: -0.1700

Data Index: 8653338 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1113. Min Act: -0.1700

Data Index: 1249598 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1586. Min Act: -0.1700

Data Index: 920527 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1464. Min Act: -0.1700

Data Index: 940045 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1426. Min Act: -0.1700

Data Index: 2783061 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1594. Min Act: -0.1700

Data Index: 5789514 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1226. Min Act: -0.1700

Data Index: 1405297 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 4.2732. Min Range: -4.2732

Max Act: 4.1217. Min Act: -0.1700

Data Index: 5867363 (Open Web Text)

Max Activating Token Index: 3