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

Dataset: Open Web Text

Neuron 2178 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: 4.9354. Min Range: -4.9354

Max Act: 4.9332. Min Act: -0.1700

Data Index: 8624489 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.9354. Min Act: -0.1700

Data Index: 7486176 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8852. Min Act: -0.1700

Data Index: 7512315 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8707. Min Act: -0.1700

Data Index: 5285628 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8500. Min Act: -0.1700

Data Index: 4035326 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8592. Min Act: -0.1700

Data Index: 7142654 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8423. Min Act: -0.1700

Data Index: 876148 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8453. Min Act: -0.1700

Data Index: 7742627 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8514. Min Act: -0.1700

Data Index: 1774231 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8350. Min Act: -0.1700

Data Index: 5047042 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8191. Min Act: -0.1700

Data Index: 5878609 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8157. Min Act: -0.1700

Data Index: 3529775 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8084. Min Act: -0.1700

Data Index: 6628222 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7951. Min Act: -0.1700

Data Index: 949456 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7821. Min Act: -0.1700

Data Index: 6227183 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.8044. Min Act: -0.1700

Data Index: 6524597 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7746. Min Act: -0.1700

Data Index: 3042641 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7843. Min Act: -0.1700

Data Index: 2510455 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7887. Min Act: -0.1700

Data Index: 3492994 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.9354. Min Range: -4.9354

Max Act: 4.7774. Min Act: -0.1700

Data Index: 1273906 (Open Web Text)

Max Activating Token Index: 5