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

Dataset: Open Web Text

Neuron 2463 in Layer 2

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: 3.3258. Min Range: -3.3258

Max Act: 3.3258. Min Act: -0.1700

Data Index: 1325618 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2902. Min Act: -0.1700

Data Index: 4462600 (Open Web Text)

Max Activating Token Index: 375

Text #2

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2284. Min Act: -0.1700

Data Index: 1108287 (Open Web Text)

Max Activating Token Index: 633

Text #3

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2790. Min Act: -0.1700

Data Index: 5959861 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2606. Min Act: -0.1700

Data Index: 1192787 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2284. Min Act: -0.1700

Data Index: 1333799 (Open Web Text)

Max Activating Token Index: 528

Text #6

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2182. Min Act: -0.1700

Data Index: 1261025 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2261. Min Act: -0.1700

Data Index: 6200664 (Open Web Text)

Max Activating Token Index: 813

Text #8

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2012. Min Act: -0.1700

Data Index: 2130512 (Open Web Text)

Max Activating Token Index: 793

Text #9

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2196. Min Act: -0.1700

Data Index: 4566920 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1819. Min Act: -0.1700

Data Index: 4496382 (Open Web Text)

Max Activating Token Index: 746

Text #11

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1886. Min Act: -0.1700

Data Index: 53232 (Open Web Text)

Max Activating Token Index: 332

Text #12

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1913. Min Act: -0.1700

Data Index: 3877281 (Open Web Text)

Max Activating Token Index: 434

Text #13

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2266. Min Act: -0.1700

Data Index: 3904380 (Open Web Text)

Max Activating Token Index: 692

Text #14

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2176. Min Act: -0.1700

Data Index: 2185822 (Open Web Text)

Max Activating Token Index: 431

Text #15

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1848. Min Act: -0.1700

Data Index: 3370126 (Open Web Text)

Max Activating Token Index: 366

Text #16

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2194. Min Act: -0.1700

Data Index: 1802435 (Open Web Text)

Max Activating Token Index: 572

Text #17

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2234. Min Act: -0.1700

Data Index: 6236010 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.1786. Min Act: -0.1700

Data Index: 8595849 (Open Web Text)

Max Activating Token Index: 949

Text #19

Max Range: 3.3258. Min Range: -3.3258

Max Act: 3.2011. Min Act: -0.1700

Data Index: 4004529 (Open Web Text)

Max Activating Token Index: 941