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

Dataset: Open Web Text

Neuron 2391 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: 3.3124. Min Range: -3.3124

Max Act: 3.3122. Min Act: -0.1700

Data Index: 7657875 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.3124. Min Act: -0.1700

Data Index: 1443373 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2655. Min Act: -0.1700

Data Index: 2365509 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2796. Min Act: -0.1700

Data Index: 2337139 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2719. Min Act: -0.1700

Data Index: 8202655 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2672. Min Act: -0.1700

Data Index: 3062607 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2316. Min Act: -0.1700

Data Index: 5987989 (Open Web Text)

Max Activating Token Index: 195

Text #7

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2365. Min Act: -0.1700

Data Index: 73171 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2471. Min Act: -0.1700

Data Index: 4693571 (Open Web Text)

Max Activating Token Index: 801

Text #9

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2257. Min Act: -0.1700

Data Index: 2986010 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2433. Min Act: -0.1700

Data Index: 7315740 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2357. Min Act: -0.1700

Data Index: 3429185 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.1951. Min Act: -0.1700

Data Index: 2702432 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2119. Min Act: -0.1700

Data Index: 4485326 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.1995. Min Act: -0.1700

Data Index: 1062007 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.1990. Min Act: -0.1700

Data Index: 4713131 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.1975. Min Act: -0.1700

Data Index: 4737198 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.1948. Min Act: -0.1700

Data Index: 4797639 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2204. Min Act: -0.1700

Data Index: 5221893 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.3124. Min Range: -3.3124

Max Act: 3.2048. Min Act: -0.1700

Data Index: 3301644 (Open Web Text)

Max Activating Token Index: 5