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

Dataset: Open Web Text

Neuron 2394 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: 4.7467. Min Range: -4.7467

Max Act: 4.7467. Min Act: -0.1700

Data Index: 3435249 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.7114. Min Act: -0.1700

Data Index: 2124358 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.7132. Min Act: -0.1700

Data Index: 4585137 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6804. Min Act: -0.1700

Data Index: 3363105 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6574. Min Act: -0.1700

Data Index: 2487635 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6572. Min Act: -0.1700

Data Index: 8766480 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6468. Min Act: -0.1700

Data Index: 385437 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6189. Min Act: -0.1700

Data Index: 5823703 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.6146. Min Act: -0.1700

Data Index: 5980777 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5678. Min Act: -0.1700

Data Index: 1555490 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5818. Min Act: -0.1700

Data Index: 615047 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5669. Min Act: -0.1700

Data Index: 7509486 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5661. Min Act: -0.1700

Data Index: 7024066 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5698. Min Act: -0.1700

Data Index: 6236246 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5826. Min Act: -0.1700

Data Index: 1746461 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5864. Min Act: -0.1700

Data Index: 5904436 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5791. Min Act: -0.1700

Data Index: 899147 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5661. Min Act: -0.1700

Data Index: 3657502 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5741. Min Act: -0.1700

Data Index: 5512613 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7467. Min Range: -4.7467

Max Act: 4.5826. Min Act: -0.1700

Data Index: 1088449 (Open Web Text)

Max Activating Token Index: 8