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

Dataset: Open Web Text

Neuron 805 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: 3.8795. Min Range: -3.8795

Max Act: 3.8723. Min Act: -0.1700

Data Index: 2040616 (Open Web Text)

Max Activating Token Index: 596

Text #1

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.8795. Min Act: -0.1700

Data Index: 7618618 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.8264. Min Act: -0.1700

Data Index: 713986 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7695. Min Act: -0.1700

Data Index: 2373173 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7898. Min Act: -0.1700

Data Index: 8074561 (Open Web Text)

Max Activating Token Index: 99

Text #5

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7877. Min Act: -0.1700

Data Index: 7021398 (Open Web Text)

Max Activating Token Index: 80

Text #6

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7970. Min Act: -0.1700

Data Index: 808015 (Open Web Text)

Max Activating Token Index: 45

Text #7

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7509. Min Act: -0.1700

Data Index: 3587188 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7537. Min Act: -0.1700

Data Index: 4285017 (Open Web Text)

Max Activating Token Index: 121

Text #9

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7623. Min Act: -0.1700

Data Index: 369507 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7748. Min Act: -0.1700

Data Index: 3163840 (Open Web Text)

Max Activating Token Index: 127

Text #11

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7529. Min Act: -0.1700

Data Index: 6569264 (Open Web Text)

Max Activating Token Index: 241

Text #12

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7507. Min Act: -0.1700

Data Index: 2146765 (Open Web Text)

Max Activating Token Index: 613

Text #13

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7349. Min Act: -0.1700

Data Index: 6768824 (Open Web Text)

Max Activating Token Index: 465

Text #14

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7393. Min Act: -0.1700

Data Index: 1695032 (Open Web Text)

Max Activating Token Index: 104

Text #15

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7449. Min Act: -0.1700

Data Index: 8028665 (Open Web Text)

Max Activating Token Index: 50

Text #16

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7354. Min Act: -0.1700

Data Index: 3777953 (Open Web Text)

Max Activating Token Index: 710

Text #17

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7210. Min Act: -0.1700

Data Index: 1635301 (Open Web Text)

Max Activating Token Index: 135

Text #18

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7275. Min Act: -0.1700

Data Index: 316956 (Open Web Text)

Max Activating Token Index: 38

Text #19

Max Range: 3.8795. Min Range: -3.8795

Max Act: 3.7181. Min Act: -0.1700

Data Index: 7767401 (Open Web Text)

Max Activating Token Index: 102