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

Dataset: Open Web Text

Neuron 1878 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: 3.6237. Min Range: -3.6237

Max Act: 3.6237. Min Act: -0.1700

Data Index: 5509665 (Open Web Text)

Max Activating Token Index: 999

Text #1

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.6128. Min Act: -0.1700

Data Index: 2273773 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5821. Min Act: -0.1700

Data Index: 6993292 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5614. Min Act: -0.1700

Data Index: 6090426 (Open Web Text)

Max Activating Token Index: 456

Text #4

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5698. Min Act: -0.1700

Data Index: 3471529 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5576. Min Act: -0.1700

Data Index: 5509666 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5516. Min Act: -0.1700

Data Index: 5856900 (Open Web Text)

Max Activating Token Index: 138

Text #7

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5903. Min Act: -0.1700

Data Index: 3028283 (Open Web Text)

Max Activating Token Index: 49

Text #8

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5820. Min Act: -0.1700

Data Index: 7767778 (Open Web Text)

Max Activating Token Index: 74

Text #9

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5847. Min Act: -0.1700

Data Index: 3163290 (Open Web Text)

Max Activating Token Index: 198

Text #10

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5375. Min Act: -0.1700

Data Index: 5745958 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5173. Min Act: -0.1700

Data Index: 4859810 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5364. Min Act: -0.1700

Data Index: 3163289 (Open Web Text)

Max Activating Token Index: 737

Text #13

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5244. Min Act: -0.1700

Data Index: 5833259 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5308. Min Act: -0.1700

Data Index: 5604241 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5504. Min Act: -0.1700

Data Index: 87397 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5301. Min Act: -0.1700

Data Index: 5149913 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5212. Min Act: -0.1700

Data Index: 4953903 (Open Web Text)

Max Activating Token Index: 144

Text #18

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5179. Min Act: -0.1700

Data Index: 4938711 (Open Web Text)

Max Activating Token Index: 349

Text #19

Max Range: 3.6237. Min Range: -3.6237

Max Act: 3.5594. Min Act: -0.1700

Data Index: 2042388 (Open Web Text)

Max Activating Token Index: 332