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

Dataset: Open Web Text

Neuron 1001 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: 3.1969. Min Range: -3.1969

Max Act: 3.1969. Min Act: -0.1700

Data Index: 2631983 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1524. Min Act: -0.1700

Data Index: 2939844 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1119. Min Act: -0.1700

Data Index: 8324009 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1092. Min Act: -0.1700

Data Index: 8708740 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.1074. Min Act: -0.1700

Data Index: 4625598 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0862. Min Act: -0.1700

Data Index: 7180377 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0738. Min Act: -0.1700

Data Index: 5764181 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0690. Min Act: -0.1700

Data Index: 1517295 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0632. Min Act: -0.1700

Data Index: 6861586 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0639. Min Act: -0.1700

Data Index: 3656285 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0678. Min Act: -0.1700

Data Index: 8371685 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0676. Min Act: -0.1700

Data Index: 77775 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0678. Min Act: -0.1700

Data Index: 5209282 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0682. Min Act: -0.1700

Data Index: 7974317 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0546. Min Act: -0.1700

Data Index: 3054493 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0488. Min Act: -0.1700

Data Index: 963633 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0521. Min Act: -0.1700

Data Index: 2942380 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0489. Min Act: -0.1700

Data Index: 986057 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0441. Min Act: -0.1700

Data Index: 6931853 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.1969. Min Range: -3.1969

Max Act: 3.0561. Min Act: -0.1700

Data Index: 7166446 (Open Web Text)

Max Activating Token Index: 4