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

Dataset: Open Web Text

Neuron 2544 in Layer 2

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: 4.2260. Min Range: -4.2260

Max Act: 4.2249. Min Act: -0.1700

Data Index: 2260814 (Open Web Text)

Max Activating Token Index: 993

Text #1

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.2254. Min Act: -0.1700

Data Index: 6504838 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1865. Min Act: -0.1700

Data Index: 3331558 (Open Web Text)

Max Activating Token Index: 850

Text #3

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.2260. Min Act: -0.1700

Data Index: 5583008 (Open Web Text)

Max Activating Token Index: 737

Text #4

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1437. Min Act: -0.1700

Data Index: 5729090 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1437. Min Act: -0.1700

Data Index: 6097438 (Open Web Text)

Max Activating Token Index: 997

Text #6

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1154. Min Act: -0.1700

Data Index: 2476235 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1126. Min Act: -0.1700

Data Index: 5642386 (Open Web Text)

Max Activating Token Index: 44

Text #8

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0943. Min Act: -0.1700

Data Index: 200584 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1165. Min Act: -0.1700

Data Index: 4870558 (Open Web Text)

Max Activating Token Index: 910

Text #10

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.1098. Min Act: -0.1700

Data Index: 2879834 (Open Web Text)

Max Activating Token Index: 962

Text #11

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0763. Min Act: -0.1700

Data Index: 8319179 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0784. Min Act: -0.1700

Data Index: 3350388 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0727. Min Act: -0.1700

Data Index: 3959577 (Open Web Text)

Max Activating Token Index: 81

Text #14

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0655. Min Act: -0.1699

Data Index: 3106985 (Open Web Text)

Max Activating Token Index: 987

Text #15

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0656. Min Act: -0.1700

Data Index: 3126123 (Open Web Text)

Max Activating Token Index: 83

Text #16

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0641. Min Act: -0.1700

Data Index: 7429603 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0400. Min Act: -0.1700

Data Index: 6485429 (Open Web Text)

Max Activating Token Index: 1005

Text #18

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0430. Min Act: -0.1700

Data Index: 3048564 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.2260. Min Range: -4.2260

Max Act: 4.0685. Min Act: -0.1700

Data Index: 1334204 (Open Web Text)

Max Activating Token Index: 985