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

Dataset: Open Web Text

Neuron 570 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: 2.5649. Min Range: -2.5649

Max Act: 2.5649. Min Act: -0.1700

Data Index: 5977170 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.5001. Min Act: -0.1700

Data Index: 3359821 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4888. Min Act: -0.1700

Data Index: 5165702 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4821. Min Act: -0.1700

Data Index: 1248237 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4630. Min Act: -0.1700

Data Index: 156424 (Open Web Text)

Max Activating Token Index: 85

Text #5

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4442. Min Act: -0.1700

Data Index: 5512562 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4450. Min Act: -0.1700

Data Index: 4356153 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4322. Min Act: -0.1700

Data Index: 7015464 (Open Web Text)

Max Activating Token Index: 34

Text #8

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4485. Min Act: -0.1700

Data Index: 1764163 (Open Web Text)

Max Activating Token Index: 912

Text #9

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4227. Min Act: -0.1700

Data Index: 1025026 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4274. Min Act: -0.1700

Data Index: 8636718 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4195. Min Act: -0.1700

Data Index: 7894969 (Open Web Text)

Max Activating Token Index: 530

Text #12

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4234. Min Act: -0.1700

Data Index: 2688622 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4209. Min Act: -0.1700

Data Index: 2569112 (Open Web Text)

Max Activating Token Index: 25

Text #14

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4309. Min Act: -0.1700

Data Index: 7525307 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4253. Min Act: -0.1700

Data Index: 1712177 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4329. Min Act: -0.1700

Data Index: 6172797 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4205. Min Act: -0.1700

Data Index: 4181517 (Open Web Text)

Max Activating Token Index: 16

Text #18

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4110. Min Act: -0.1700

Data Index: 3250822 (Open Web Text)

Max Activating Token Index: 20

Text #19

Max Range: 2.5649. Min Range: -2.5649

Max Act: 2.4225. Min Act: -0.1700

Data Index: 1386461 (Open Web Text)

Max Activating Token Index: 178