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

Dataset: Open Web Text

Neuron 379 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: 5.7682. Min Range: -5.7682

Max Act: 5.7682. Min Act: -0.1700

Data Index: 8094218 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.7440. Min Act: -0.1700

Data Index: 5356054 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.7288. Min Act: -0.1700

Data Index: 5166020 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.7072. Min Act: -0.1700

Data Index: 8194959 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.7092. Min Act: -0.1700

Data Index: 1157974 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6757. Min Act: -0.1700

Data Index: 230730 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6617. Min Act: -0.1700

Data Index: 8002387 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6954. Min Act: -0.1700

Data Index: 6140504 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6913. Min Act: -0.1700

Data Index: 1881353 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6514. Min Act: -0.1700

Data Index: 8477640 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6364. Min Act: -0.1700

Data Index: 7240583 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6610. Min Act: -0.1700

Data Index: 8406933 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6572. Min Act: -0.1700

Data Index: 6284053 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6337. Min Act: -0.1700

Data Index: 8370835 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6525. Min Act: -0.1700

Data Index: 475928 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6356. Min Act: -0.1700

Data Index: 5527089 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6412. Min Act: -0.1700

Data Index: 5225408 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6590. Min Act: -0.1700

Data Index: 1387331 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6457. Min Act: -0.1700

Data Index: 7680147 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 5.7682. Min Range: -5.7682

Max Act: 5.6514. Min Act: -0.1700

Data Index: 7297930 (Open Web Text)

Max Activating Token Index: 4