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

Dataset: Open Web Text

Neuron 2484 in Layer 4

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: 2.0686. Min Range: -2.0686

Max Act: 2.0686. Min Act: -0.1700

Data Index: 4165738 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 2.0686. Min Range: -2.0686

Max Act: 2.0182. Min Act: -0.1700

Data Index: 8445700 (Open Web Text)

Max Activating Token Index: 56

Text #2

Max Range: 2.0686. Min Range: -2.0686

Max Act: 2.0002. Min Act: -0.1700

Data Index: 3432869 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9683. Min Act: -0.1700

Data Index: 43243 (Open Web Text)

Max Activating Token Index: 56

Text #4

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9626. Min Act: -0.1700

Data Index: 3065965 (Open Web Text)

Max Activating Token Index: 52

Text #5

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9577. Min Act: -0.1700

Data Index: 4341221 (Open Web Text)

Max Activating Token Index: 48

Text #6

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9499. Min Act: -0.1700

Data Index: 7239020 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9377. Min Act: -0.1700

Data Index: 1431885 (Open Web Text)

Max Activating Token Index: 50

Text #8

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9215. Min Act: -0.1700

Data Index: 62029 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9317. Min Act: -0.1700

Data Index: 3466138 (Open Web Text)

Max Activating Token Index: 64

Text #10

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9144. Min Act: -0.1700

Data Index: 2045315 (Open Web Text)

Max Activating Token Index: 273

Text #11

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9175. Min Act: -0.1700

Data Index: 65997 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9153. Min Act: -0.1700

Data Index: 7144110 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9131. Min Act: -0.1700

Data Index: 4901580 (Open Web Text)

Max Activating Token Index: 49

Text #14

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9106. Min Act: -0.1700

Data Index: 6226523 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9020. Min Act: -0.1700

Data Index: 6958334 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9122. Min Act: -0.1700

Data Index: 5584121 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9056. Min Act: -0.1700

Data Index: 4496656 (Open Web Text)

Max Activating Token Index: 295

Text #18

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9051. Min Act: -0.1700

Data Index: 4377475 (Open Web Text)

Max Activating Token Index: 68

Text #19

Max Range: 2.0686. Min Range: -2.0686

Max Act: 1.9187. Min Act: -0.1700

Data Index: 3832911 (Open Web Text)

Max Activating Token Index: 59