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

Dataset: Open Web Text

Neuron 1196 in Layer 4

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: 3.6189. Min Range: -3.6189

Max Act: 3.6189. Min Act: -0.1700

Data Index: 6826968 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5592. Min Act: -0.1700

Data Index: 3310499 (Open Web Text)

Max Activating Token Index: 297

Text #2

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5180. Min Act: -0.1700

Data Index: 8270906 (Open Web Text)

Max Activating Token Index: 737

Text #3

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.5062. Min Act: -0.1700

Data Index: 7349500 (Open Web Text)

Max Activating Token Index: 555

Text #4

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4898. Min Act: -0.1700

Data Index: 6963744 (Open Web Text)

Max Activating Token Index: 399

Text #5

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4846. Min Act: -0.1700

Data Index: 6234028 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4284. Min Act: -0.1700

Data Index: 2803980 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.4019. Min Act: -0.1700

Data Index: 6529640 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3853. Min Act: -0.1700

Data Index: 7700800 (Open Web Text)

Max Activating Token Index: 483

Text #9

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3654. Min Act: -0.1700

Data Index: 3098660 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3576. Min Act: -0.1700

Data Index: 6273084 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3611. Min Act: -0.1700

Data Index: 607121 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3368. Min Act: -0.1700

Data Index: 607120 (Open Web Text)

Max Activating Token Index: 827

Text #13

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3348. Min Act: -0.1700

Data Index: 4288249 (Open Web Text)

Max Activating Token Index: 330

Text #14

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3257. Min Act: -0.1700

Data Index: 4395243 (Open Web Text)

Max Activating Token Index: 230

Text #15

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3227. Min Act: -0.1700

Data Index: 6834116 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.2974. Min Act: -0.1700

Data Index: 7152365 (Open Web Text)

Max Activating Token Index: 998

Text #17

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3097. Min Act: -0.1700

Data Index: 6762509 (Open Web Text)

Max Activating Token Index: 639

Text #18

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.3019. Min Act: -0.1700

Data Index: 7471262 (Open Web Text)

Max Activating Token Index: 890

Text #19

Max Range: 3.6189. Min Range: -3.6189

Max Act: 3.2938. Min Act: -0.1700

Data Index: 1977557 (Open Web Text)

Max Activating Token Index: 983