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

Dataset: Open Web Text

Neuron 1080 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: 5.3298. Min Range: -5.3298

Max Act: 5.3298. Min Act: -0.1700

Data Index: 7785279 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.2302. Min Act: -0.1700

Data Index: 3202218 (Open Web Text)

Max Activating Token Index: 32

Text #2

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.1572. Min Act: -0.1700

Data Index: 4971160 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.1266. Min Act: -0.1700

Data Index: 4687552 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.1299. Min Act: -0.1700

Data Index: 2870277 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.1364. Min Act: -0.1700

Data Index: 5139827 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0997. Min Act: -0.1700

Data Index: 7151958 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0895. Min Act: -0.1700

Data Index: 1799973 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0703. Min Act: -0.1700

Data Index: 5583578 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0655. Min Act: -0.1700

Data Index: 3865267 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0306. Min Act: -0.1700

Data Index: 5462148 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9880. Min Act: -0.1700

Data Index: 2103954 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9851. Min Act: -0.1700

Data Index: 6730738 (Open Web Text)

Max Activating Token Index: 22

Text #13

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0124. Min Act: -0.1700

Data Index: 863830 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9850. Min Act: -0.1700

Data Index: 5466976 (Open Web Text)

Max Activating Token Index: 826

Text #15

Max Range: 5.3298. Min Range: -5.3298

Max Act: 5.0090. Min Act: -0.1700

Data Index: 5835958 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9686. Min Act: -0.1700

Data Index: 2287634 (Open Web Text)

Max Activating Token Index: 14

Text #17

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9729. Min Act: -0.1700

Data Index: 198323 (Open Web Text)

Max Activating Token Index: 724

Text #18

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9609. Min Act: -0.1700

Data Index: 1964264 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 5.3298. Min Range: -5.3298

Max Act: 4.9596. Min Act: -0.1700

Data Index: 4578611 (Open Web Text)

Max Activating Token Index: 6