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

Dataset: Open Web Text

Neuron 1724 in Layer 1

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: 4.3872. Min Range: -4.3872

Max Act: 4.3872. Min Act: -0.1700

Data Index: 7373232 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2782. Min Act: -0.1700

Data Index: 5979055 (Open Web Text)

Max Activating Token Index: 420

Text #2

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2674. Min Act: -0.1700

Data Index: 3944611 (Open Web Text)

Max Activating Token Index: 178

Text #3

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2882. Min Act: -0.1700

Data Index: 3990611 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2381. Min Act: -0.1700

Data Index: 3699850 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2315. Min Act: -0.1700

Data Index: 5969072 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2367. Min Act: -0.1700

Data Index: 2197884 (Open Web Text)

Max Activating Token Index: 490

Text #7

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2337. Min Act: -0.1700

Data Index: 4831674 (Open Web Text)

Max Activating Token Index: 286

Text #8

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2190. Min Act: -0.1700

Data Index: 473071 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2187. Min Act: -0.1700

Data Index: 3290378 (Open Web Text)

Max Activating Token Index: 173

Text #10

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1971. Min Act: -0.1700

Data Index: 8263305 (Open Web Text)

Max Activating Token Index: 934

Text #11

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2020. Min Act: -0.1700

Data Index: 8154135 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2070. Min Act: -0.1700

Data Index: 3983850 (Open Web Text)

Max Activating Token Index: 589

Text #13

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1951. Min Act: -0.1700

Data Index: 7171356 (Open Web Text)

Max Activating Token Index: 700

Text #14

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.2018. Min Act: -0.1700

Data Index: 4560273 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1808. Min Act: -0.1700

Data Index: 4883817 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1851. Min Act: -0.1700

Data Index: 5697252 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1809. Min Act: -0.1700

Data Index: 1549912 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1808. Min Act: -0.1700

Data Index: 5718033 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.3872. Min Range: -4.3872

Max Act: 4.1803. Min Act: -0.1700

Data Index: 3804613 (Open Web Text)

Max Activating Token Index: 179