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

Dataset: Open Web Text

Neuron 1544 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: 2.5195. Min Range: -2.5195

Max Act: 2.5195. Min Act: -0.1700

Data Index: 6228440 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.5099. Min Act: -0.1700

Data Index: 4589291 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4753. Min Act: -0.1700

Data Index: 7337408 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4657. Min Act: -0.1700

Data Index: 3381015 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4598. Min Act: -0.1700

Data Index: 5916190 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4484. Min Act: -0.1700

Data Index: 3793032 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4448. Min Act: -0.1700

Data Index: 6324434 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4441. Min Act: -0.1700

Data Index: 448609 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4278. Min Act: -0.1700

Data Index: 1285094 (Open Web Text)

Max Activating Token Index: 910

Text #9

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4162. Min Act: -0.1700

Data Index: 8620147 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4233. Min Act: -0.1700

Data Index: 3131964 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4275. Min Act: -0.1700

Data Index: 1295148 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4222. Min Act: -0.1700

Data Index: 8387027 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4279. Min Act: -0.1700

Data Index: 3515290 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4215. Min Act: -0.1700

Data Index: 2551543 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4003. Min Act: -0.1700

Data Index: 8244806 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4003. Min Act: -0.1700

Data Index: 8416409 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4036. Min Act: -0.1700

Data Index: 7797124 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.4018. Min Act: -0.1700

Data Index: 4884120 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 2.5195. Min Range: -2.5195

Max Act: 2.3940. Min Act: -0.1700

Data Index: 6824227 (Open Web Text)

Max Activating Token Index: 386