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

Dataset: Open Web Text

Neuron 2793 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: 3.7460. Min Range: -3.7460

Max Act: 3.7460. Min Act: -0.1700

Data Index: 6154454 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7460. Min Act: -0.1700

Data Index: 8360699 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7460. Min Act: -0.1700

Data Index: 5825679 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7460. Min Act: -0.1700

Data Index: 7985178 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7460. Min Act: -0.1700

Data Index: 5705558 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7239. Min Act: -0.1700

Data Index: 4039884 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.7011. Min Act: -0.1700

Data Index: 701204 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.6287. Min Act: -0.1700

Data Index: 5839596 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.6368. Min Act: -0.1700

Data Index: 5774616 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5974. Min Act: -0.1700

Data Index: 8110688 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5751. Min Act: -0.1700

Data Index: 5442269 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5943. Min Act: -0.1700

Data Index: 2626333 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5876. Min Act: -0.1700

Data Index: 1090442 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5617. Min Act: -0.1700

Data Index: 5589752 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5627. Min Act: -0.1700

Data Index: 3192174 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5617. Min Act: -0.1700

Data Index: 4407790 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5162. Min Act: -0.1700

Data Index: 3815214 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5157. Min Act: -0.1700

Data Index: 1383303 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5173. Min Act: -0.1700

Data Index: 3052995 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.7460. Min Range: -3.7460

Max Act: 3.5208. Min Act: -0.1700

Data Index: 6257788 (Open Web Text)

Max Activating Token Index: 5