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

Dataset: Open Web Text

Neuron 2589 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: 3.6936. Min Range: -3.6936

Max Act: 3.6936. Min Act: -0.1700

Data Index: 6162807 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6766. Min Act: -0.1700

Data Index: 8508269 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6391. Min Act: -0.1700

Data Index: 7399197 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6230. Min Act: -0.1700

Data Index: 8204615 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6359. Min Act: -0.1700

Data Index: 921126 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6292. Min Act: -0.1700

Data Index: 2324792 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6084. Min Act: -0.1700

Data Index: 6528883 (Open Web Text)

Max Activating Token Index: 664

Text #7

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6173. Min Act: -0.1700

Data Index: 6909379 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6248. Min Act: -0.1700

Data Index: 8631519 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6023. Min Act: -0.1700

Data Index: 8828845 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.6023. Min Act: -0.1700

Data Index: 5889207 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5980. Min Act: -0.1700

Data Index: 5342556 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5728. Min Act: -0.1700

Data Index: 2922649 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5869. Min Act: -0.1700

Data Index: 6129250 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5869. Min Act: -0.1700

Data Index: 6001206 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5806. Min Act: -0.1700

Data Index: 5691190 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5927. Min Act: -0.1700

Data Index: 5010836 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1894745 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5704. Min Act: -0.1700

Data Index: 1858076 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.6936. Min Range: -3.6936

Max Act: 3.5869. Min Act: -0.1700

Data Index: 1712964 (Open Web Text)

Max Activating Token Index: 2