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

Dataset: Open Web Text

Neuron 1701 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: 0.7574. Min Range: -0.7574

Max Act: 0.7511. Min Act: -0.1700

Data Index: 8648251 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7542. Min Act: -0.1700

Data Index: 8727118 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7556. Min Act: -0.1700

Data Index: 440659 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7503. Min Act: -0.1700

Data Index: 5530032 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7453. Min Act: -0.1700

Data Index: 7158506 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7467. Min Act: -0.1700

Data Index: 8389684 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7574. Min Act: -0.1700

Data Index: 7949598 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7476. Min Act: -0.1700

Data Index: 6707732 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7395. Min Act: -0.1700

Data Index: 3773976 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7362. Min Act: -0.1700

Data Index: 3856235 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7380. Min Act: -0.1700

Data Index: 4616150 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7373. Min Act: -0.1700

Data Index: 4432052 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7470. Min Act: -0.1700

Data Index: 821925 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7321. Min Act: -0.1700

Data Index: 2634256 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7356. Min Act: -0.1700

Data Index: 5478009 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7369. Min Act: -0.1700

Data Index: 8191907 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7340. Min Act: -0.1700

Data Index: 2320249 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7282. Min Act: -0.1700

Data Index: 370284 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7298. Min Act: -0.1700

Data Index: 7708312 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 0.7574. Min Range: -0.7574

Max Act: 0.7321. Min Act: -0.1700

Data Index: 1758194 (Open Web Text)

Max Activating Token Index: 3