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

Dataset: Open Web Text

Neuron 2789 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: 1.6140. Min Range: -1.6140

Max Act: 1.6140. Min Act: -0.1700

Data Index: 1907308 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5791. Min Act: -0.1700

Data Index: 3338531 (Open Web Text)

Max Activating Token Index: 556

Text #2

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5712. Min Act: -0.1700

Data Index: 6995458 (Open Web Text)

Max Activating Token Index: 683

Text #3

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5478. Min Act: -0.1700

Data Index: 1256390 (Open Web Text)

Max Activating Token Index: 370

Text #4

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5460. Min Act: -0.1700

Data Index: 1845928 (Open Web Text)

Max Activating Token Index: 346

Text #5

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5285. Min Act: -0.1700

Data Index: 1410848 (Open Web Text)

Max Activating Token Index: 572

Text #6

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5307. Min Act: -0.1699

Data Index: 8645879 (Open Web Text)

Max Activating Token Index: 173

Text #7

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5320. Min Act: -0.1690

Data Index: 4647934 (Open Web Text)

Max Activating Token Index: 487

Text #8

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5263. Min Act: -0.1699

Data Index: 2200095 (Open Web Text)

Max Activating Token Index: 516

Text #9

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5274. Min Act: -0.1700

Data Index: 6725989 (Open Web Text)

Max Activating Token Index: 531

Text #10

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5157. Min Act: -0.1700

Data Index: 1783727 (Open Web Text)

Max Activating Token Index: 532

Text #11

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5128. Min Act: -0.1689

Data Index: 4517746 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5098. Min Act: -0.1700

Data Index: 7220479 (Open Web Text)

Max Activating Token Index: 557

Text #13

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5159. Min Act: -0.1700

Data Index: 2243293 (Open Web Text)

Max Activating Token Index: 280

Text #14

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5057. Min Act: -0.1699

Data Index: 153314 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5015. Min Act: -0.1698

Data Index: 2063639 (Open Web Text)

Max Activating Token Index: 302

Text #16

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5088. Min Act: -0.1700

Data Index: 3513683 (Open Web Text)

Max Activating Token Index: 377

Text #17

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5053. Min Act: -0.1700

Data Index: 2993049 (Open Web Text)

Max Activating Token Index: 97

Text #18

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5041. Min Act: -0.1700

Data Index: 1368023 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 1.6140. Min Range: -1.6140

Max Act: 1.5069. Min Act: -0.1700

Data Index: 1868858 (Open Web Text)

Max Activating Token Index: 587