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

Dataset: Open Web Text

Neuron 1790 in Layer 5

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: 5.7237. Min Range: -5.7237

Max Act: 5.7237. Min Act: -0.1574

Data Index: 5561092 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.3389. Min Act: -0.0101

Data Index: 3503597 (Open Web Text)

Max Activating Token Index: 700

Text #2

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.3285. Min Act: -0.0101

Data Index: 5702925 (Open Web Text)

Max Activating Token Index: 331

Text #3

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.3052. Min Act: -0.0101

Data Index: 6059450 (Open Web Text)

Max Activating Token Index: 881

Text #4

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.2209. Min Act: -0.0101

Data Index: 5175755 (Open Web Text)

Max Activating Token Index: 441

Text #5

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.2241. Min Act: -0.0101

Data Index: 3684834 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.2015. Min Act: -0.0101

Data Index: 3513885 (Open Web Text)

Max Activating Token Index: 211

Text #7

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1909. Min Act: -0.0101

Data Index: 968514 (Open Web Text)

Max Activating Token Index: 352

Text #8

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1671. Min Act: -0.0101

Data Index: 8505572 (Open Web Text)

Max Activating Token Index: 482

Text #9

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1905. Min Act: -0.0101

Data Index: 6763857 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1769. Min Act: -0.0101

Data Index: 5175736 (Open Web Text)

Max Activating Token Index: 402

Text #11

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1460. Min Act: -0.0101

Data Index: 7600645 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1362. Min Act: -0.0101

Data Index: 2910247 (Open Web Text)

Max Activating Token Index: 971

Text #13

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1159. Min Act: -0.0101

Data Index: 5175737 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.0995. Min Act: -0.0101

Data Index: 7805949 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1219. Min Act: -0.0293

Data Index: 5656133 (Open Web Text)

Max Activating Token Index: 354

Text #16

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1221. Min Act: -0.0101

Data Index: 5931848 (Open Web Text)

Max Activating Token Index: 985

Text #17

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1336. Min Act: -0.0101

Data Index: 4384008 (Open Web Text)

Max Activating Token Index: 547

Text #18

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.1001. Min Act: -0.0101

Data Index: 2910244 (Open Web Text)

Max Activating Token Index: 577

Text #19

Max Range: 5.7237. Min Range: -5.7237

Max Act: 5.0861. Min Act: -0.0101

Data Index: 5931849 (Open Web Text)

Max Activating Token Index: 209