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

Dataset: Open Web Text

Neuron 206 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: 2.9901. Min Range: -2.9901

Max Act: 2.9901. Min Act: -0.1700

Data Index: 6413285 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9369. Min Act: -0.1700

Data Index: 5484317 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9369. Min Act: -0.1700

Data Index: 80953 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.9015. Min Act: -0.1700

Data Index: 5752558 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8776. Min Act: -0.1700

Data Index: 7092751 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8784. Min Act: -0.1700

Data Index: 6578762 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8655. Min Act: -0.1700

Data Index: 8796040 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8686. Min Act: -0.1700

Data Index: 8108247 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8348. Min Act: -0.1700

Data Index: 7284398 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8317. Min Act: -0.1700

Data Index: 7328190 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8354. Min Act: -0.1700

Data Index: 5820413 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 6571577 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 2499503 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 5269627 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8276. Min Act: -0.1700

Data Index: 3996370 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 6424994 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 4691589 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8227. Min Act: -0.1700

Data Index: 6093456 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8076. Min Act: -0.1700

Data Index: 4970765 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.9901. Min Range: -2.9901

Max Act: 2.8050. Min Act: -0.1700

Data Index: 5282064 (Open Web Text)

Max Activating Token Index: 4