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

Dataset: Open Web Text

Neuron 1491 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: 1.6858. Min Range: -1.6858

Max Act: 1.6858. Min Act: -0.1700

Data Index: 374013 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.6678. Min Act: -0.1700

Data Index: 3561027 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.6522. Min Act: -0.1700

Data Index: 5476536 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.6432. Min Act: -0.1700

Data Index: 995390 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.6089. Min Act: -0.1700

Data Index: 7121816 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5946. Min Act: -0.1700

Data Index: 7955174 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5549. Min Act: -0.1700

Data Index: 1035808 (Open Web Text)

Max Activating Token Index: 29

Text #7

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5590. Min Act: -0.1700

Data Index: 7825455 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5546. Min Act: -0.1700

Data Index: 3816306 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5533. Min Act: -0.1700

Data Index: 2370022 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5429. Min Act: -0.1700

Data Index: 5568737 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5337. Min Act: -0.1700

Data Index: 7522742 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5089. Min Act: -0.1700

Data Index: 2525363 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.4983. Min Act: -0.1700

Data Index: 3303119 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5014. Min Act: -0.1700

Data Index: 4647306 (Open Web Text)

Max Activating Token Index: 41

Text #15

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.5025. Min Act: -0.1700

Data Index: 2799470 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.4855. Min Act: -0.1700

Data Index: 1875482 (Open Web Text)

Max Activating Token Index: 9

Text #17

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.4863. Min Act: -0.1700

Data Index: 3246067 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.4863. Min Act: -0.1700

Data Index: 6448445 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 1.6858. Min Range: -1.6858

Max Act: 1.4854. Min Act: -0.1700

Data Index: 5862620 (Open Web Text)

Max Activating Token Index: 122