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

Dataset: Open Web Text

Neuron 160 in Layer 3

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: 2.8318. Min Range: -2.8318

Max Act: 2.8318. Min Act: -0.1700

Data Index: 6750847 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6522. Min Act: -0.1700

Data Index: 3490223 (Open Web Text)

Max Activating Token Index: 544

Text #2

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6365. Min Act: -0.1700

Data Index: 7394987 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6328. Min Act: -0.1700

Data Index: 2986292 (Open Web Text)

Max Activating Token Index: 269

Text #4

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6233. Min Act: -0.1700

Data Index: 3386983 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6331. Min Act: -0.1700

Data Index: 5952526 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.6331. Min Act: -0.1700

Data Index: 7569944 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5828. Min Act: -0.1700

Data Index: 4261320 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5862. Min Act: -0.1700

Data Index: 1539274 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 6367043 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 4770346 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 5084802 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 4394339 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 5635655 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 1788459 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 4030335 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 5441482 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5712. Min Act: -0.1700

Data Index: 2338672 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5805. Min Act: -0.1700

Data Index: 4587274 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8318. Min Range: -2.8318

Max Act: 2.5622. Min Act: -0.1700

Data Index: 4666148 (Open Web Text)

Max Activating Token Index: 4