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

Dataset: Open Web Text

Neuron 2081 in Layer 5

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: 3.0968. Min Range: -3.0968

Max Act: 3.0591. Min Act: -0.1700

Data Index: 3438120 (Open Web Text)

Max Activating Token Index: 937

Text #1

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0968. Min Act: -0.1700

Data Index: 610117 (Open Web Text)

Max Activating Token Index: 555

Text #2

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0863. Min Act: -0.1700

Data Index: 7547970 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0847. Min Act: -0.1700

Data Index: 2510072 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0910. Min Act: -0.1700

Data Index: 8689944 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0876. Min Act: -0.1700

Data Index: 8524033 (Open Web Text)

Max Activating Token Index: 36

Text #6

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0637. Min Act: -0.1700

Data Index: 7657162 (Open Web Text)

Max Activating Token Index: 35

Text #7

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0730. Min Act: -0.1700

Data Index: 638867 (Open Web Text)

Max Activating Token Index: 40

Text #8

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0764. Min Act: -0.1700

Data Index: 6854435 (Open Web Text)

Max Activating Token Index: 55

Text #9

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0637. Min Act: -0.1700

Data Index: 810512 (Open Web Text)

Max Activating Token Index: 35

Text #10

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0842. Min Act: -0.1700

Data Index: 6731421 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0730. Min Act: -0.1700

Data Index: 1414318 (Open Web Text)

Max Activating Token Index: 40

Text #12

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0530. Min Act: -0.1700

Data Index: 7282565 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0625. Min Act: -0.1700

Data Index: 592186 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0625. Min Act: -0.1700

Data Index: 4115520 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0530. Min Act: -0.1700

Data Index: 3217403 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0625. Min Act: -0.1700

Data Index: 1345790 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0697. Min Act: -0.1700

Data Index: 5934814 (Open Web Text)

Max Activating Token Index: 945

Text #18

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0620. Min Act: -0.1700

Data Index: 2211289 (Open Web Text)

Max Activating Token Index: 492

Text #19

Max Range: 3.0968. Min Range: -3.0968

Max Act: 3.0412. Min Act: -0.1700

Data Index: 7025302 (Open Web Text)

Max Activating Token Index: 825