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

Dataset: Open Web Text

Neuron 21 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: 4.5424. Min Range: -4.5424

Max Act: 4.5424. Min Act: -0.1700

Data Index: 8465233 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.4398. Min Act: -0.1700

Data Index: 1858305 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3834. Min Act: -0.1700

Data Index: 6560647 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3860. Min Act: -0.1700

Data Index: 1509962 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3564. Min Act: -0.1700

Data Index: 506949 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3564. Min Act: -0.1700

Data Index: 5599041 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3183. Min Act: -0.1700

Data Index: 2051588 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2926. Min Act: -0.1700

Data Index: 871286 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3215. Min Act: -0.1700

Data Index: 3536959 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.3135. Min Act: -0.1700

Data Index: 8465231 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2892. Min Act: -0.1700

Data Index: 2389761 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2815. Min Act: -0.1700

Data Index: 6325025 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2632. Min Act: -0.1700

Data Index: 1216349 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2797. Min Act: -0.1700

Data Index: 8030262 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2521. Min Act: -0.1700

Data Index: 7956815 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2632. Min Act: -0.1700

Data Index: 3612734 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2632. Min Act: -0.1700

Data Index: 7748858 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2898. Min Act: -0.1700

Data Index: 7198942 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2464. Min Act: -0.1700

Data Index: 2185436 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 4.5424. Min Range: -4.5424

Max Act: 4.2310. Min Act: -0.1700

Data Index: 6223263 (Open Web Text)

Max Activating Token Index: 6