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

Dataset: Open Web Text

Neuron 491 in Layer 1

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: 1.4896. Min Range: -1.4896

Max Act: 1.4896. Min Act: -0.1700

Data Index: 6712197 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4855. Min Act: -0.1700

Data Index: 8569980 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4682. Min Act: -0.1700

Data Index: 6464920 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4749. Min Act: -0.1700

Data Index: 6323397 (Open Web Text)

Max Activating Token Index: 33

Text #4

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4742. Min Act: -0.1700

Data Index: 3255241 (Open Web Text)

Max Activating Token Index: 59

Text #5

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4534. Min Act: -0.1700

Data Index: 4629189 (Open Web Text)

Max Activating Token Index: 47

Text #6

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4477. Min Act: -0.1700

Data Index: 419004 (Open Web Text)

Max Activating Token Index: 72

Text #7

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4499. Min Act: -0.1700

Data Index: 8513784 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4361. Min Act: -0.1700

Data Index: 2117196 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4359. Min Act: -0.1700

Data Index: 3142644 (Open Web Text)

Max Activating Token Index: 34

Text #10

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4234. Min Act: -0.1700

Data Index: 2547361 (Open Web Text)

Max Activating Token Index: 33

Text #11

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4229. Min Act: -0.1700

Data Index: 1791469 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4293. Min Act: -0.1700

Data Index: 6028742 (Open Web Text)

Max Activating Token Index: 73

Text #13

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4233. Min Act: -0.1700

Data Index: 7282806 (Open Web Text)

Max Activating Token Index: 77

Text #14

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4297. Min Act: -0.1700

Data Index: 5156732 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4085. Min Act: -0.1700

Data Index: 243112 (Open Web Text)

Max Activating Token Index: 59

Text #16

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4008. Min Act: -0.1700

Data Index: 43701 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4090. Min Act: -0.1700

Data Index: 5613684 (Open Web Text)

Max Activating Token Index: 62

Text #18

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4053. Min Act: -0.1700

Data Index: 5856701 (Open Web Text)

Max Activating Token Index: 85

Text #19

Max Range: 1.4896. Min Range: -1.4896

Max Act: 1.4119. Min Act: -0.1700

Data Index: 1807767 (Open Web Text)

Max Activating Token Index: 57