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

Dataset: Open Web Text

Neuron 27 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: 4.7253. Min Range: -4.7253

Max Act: 4.7253. Min Act: -0.1700

Data Index: 4028288 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6488. Min Act: -0.1700

Data Index: 8386242 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6745. Min Act: -0.1700

Data Index: 5211769 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6763. Min Act: -0.1700

Data Index: 1686799 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6370. Min Act: -0.1700

Data Index: 8622543 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6157. Min Act: -0.1700

Data Index: 1039392 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.6129. Min Act: -0.1700

Data Index: 3223679 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5551. Min Act: -0.1700

Data Index: 472751 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5628. Min Act: -0.1700

Data Index: 2284626 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5792. Min Act: -0.1700

Data Index: 8198106 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5869. Min Act: -0.1700

Data Index: 7965226 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5622. Min Act: -0.1700

Data Index: 7471111 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5676. Min Act: -0.1700

Data Index: 6453751 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5661. Min Act: -0.1700

Data Index: 1160627 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5903. Min Act: -0.1700

Data Index: 2931570 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5757. Min Act: -0.1700

Data Index: 5941432 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5901. Min Act: -0.1700

Data Index: 5551447 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5669. Min Act: -0.1700

Data Index: 5085367 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5851. Min Act: -0.1700

Data Index: 2299447 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7253. Min Range: -4.7253

Max Act: 4.5706. Min Act: -0.1700

Data Index: 4446287 (Open Web Text)

Max Activating Token Index: 4