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

Dataset: Open Web Text

Neuron 1893 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: 5.3722. Min Range: -5.3722

Max Act: 5.3722. Min Act: -0.1700

Data Index: 4284098 (Open Web Text)

Max Activating Token Index: 17

Text #1

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.3045. Min Act: -0.1700

Data Index: 6969417 (Open Web Text)

Max Activating Token Index: 480

Text #2

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.2926. Min Act: -0.1700

Data Index: 2445538 (Open Web Text)

Max Activating Token Index: 612

Text #3

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.2451. Min Act: -0.1700

Data Index: 2848354 (Open Web Text)

Max Activating Token Index: 139

Text #4

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.2105. Min Act: -0.1700

Data Index: 1594713 (Open Web Text)

Max Activating Token Index: 82

Text #5

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1989. Min Act: -0.1700

Data Index: 4101529 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.2035. Min Act: -0.1700

Data Index: 5501360 (Open Web Text)

Max Activating Token Index: 491

Text #7

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1824. Min Act: -0.1700

Data Index: 4523551 (Open Web Text)

Max Activating Token Index: 168

Text #8

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1795. Min Act: -0.1700

Data Index: 6945370 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1919. Min Act: -0.1700

Data Index: 6830450 (Open Web Text)

Max Activating Token Index: 43

Text #10

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1931. Min Act: -0.1700

Data Index: 6817544 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1658. Min Act: -0.1700

Data Index: 8214774 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1784. Min Act: -0.1700

Data Index: 8637659 (Open Web Text)

Max Activating Token Index: 67

Text #13

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1542. Min Act: -0.1700

Data Index: 4838311 (Open Web Text)

Max Activating Token Index: 38

Text #14

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1664. Min Act: -0.1700

Data Index: 6395578 (Open Web Text)

Max Activating Token Index: 137

Text #15

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1536. Min Act: -0.1700

Data Index: 372872 (Open Web Text)

Max Activating Token Index: 290

Text #16

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1300. Min Act: -0.1700

Data Index: 3064809 (Open Web Text)

Max Activating Token Index: 239

Text #17

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1190. Min Act: -0.1700

Data Index: 1561660 (Open Web Text)

Max Activating Token Index: 541

Text #18

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1375. Min Act: -0.1700

Data Index: 3084905 (Open Web Text)

Max Activating Token Index: 91

Text #19

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1312. Min Act: -0.1700

Data Index: 2614849 (Open Web Text)

Max Activating Token Index: 16