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

Dataset: Open Web Text

Neuron 1582 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: 5.1948. Min Range: -5.1948

Max Act: 5.1948. Min Act: -0.1700

Data Index: 5736275 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1045. Min Act: -0.1700

Data Index: 6981611 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1159. Min Act: -0.1700

Data Index: 4790733 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0757. Min Act: -0.1700

Data Index: 4624470 (Open Web Text)

Max Activating Token Index: 795

Text #4

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0999. Min Act: -0.1700

Data Index: 7491571 (Open Web Text)

Max Activating Token Index: 869

Text #5

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0435. Min Act: -0.1700

Data Index: 3169020 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0451. Min Act: -0.1700

Data Index: 3610758 (Open Web Text)

Max Activating Token Index: 846

Text #7

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9893. Min Act: -0.1700

Data Index: 5714720 (Open Web Text)

Max Activating Token Index: 863

Text #8

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0411. Min Act: -0.1700

Data Index: 501494 (Open Web Text)

Max Activating Token Index: 902

Text #9

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0082. Min Act: -0.1700

Data Index: 8137076 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9908. Min Act: -0.1700

Data Index: 7305467 (Open Web Text)

Max Activating Token Index: 864

Text #11

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0234. Min Act: -0.1700

Data Index: 7282421 (Open Web Text)

Max Activating Token Index: 836

Text #12

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9986. Min Act: -0.1700

Data Index: 1716452 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9694. Min Act: -0.1700

Data Index: 775673 (Open Web Text)

Max Activating Token Index: 406

Text #14

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9587. Min Act: -0.1700

Data Index: 4648077 (Open Web Text)

Max Activating Token Index: 928

Text #15

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9712. Min Act: -0.1700

Data Index: 2664033 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0120. Min Act: -0.1700

Data Index: 5093228 (Open Web Text)

Max Activating Token Index: 809

Text #17

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9640. Min Act: -0.1700

Data Index: 5523529 (Open Web Text)

Max Activating Token Index: 795

Text #18

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9969. Min Act: -0.1700

Data Index: 5645492 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9298. Min Act: -0.1700

Data Index: 5704674 (Open Web Text)

Max Activating Token Index: 923