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

Dataset: Open Web Text

Neuron 1195 in Layer 3

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: 4.3618. Min Range: -4.3618

Max Act: 4.3618. Min Act: -0.1700

Data Index: 7504053 (Open Web Text)

Max Activating Token Index: 756

Text #1

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.9779. Min Act: -0.1700

Data Index: 88284 (Open Web Text)

Max Activating Token Index: 265

Text #2

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.9355. Min Act: -0.1700

Data Index: 5017550 (Open Web Text)

Max Activating Token Index: 234

Text #3

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.9228. Min Act: -0.1700

Data Index: 4082737 (Open Web Text)

Max Activating Token Index: 232

Text #4

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8945. Min Act: -0.1700

Data Index: 6673384 (Open Web Text)

Max Activating Token Index: 707

Text #5

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.9074. Min Act: -0.1700

Data Index: 1596062 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8706. Min Act: -0.1700

Data Index: 326367 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8639. Min Act: -0.1700

Data Index: 5807596 (Open Web Text)

Max Activating Token Index: 194

Text #8

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8360. Min Act: -0.1700

Data Index: 326372 (Open Web Text)

Max Activating Token Index: 814

Text #9

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8365. Min Act: -0.1700

Data Index: 5973871 (Open Web Text)

Max Activating Token Index: 535

Text #10

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8470. Min Act: -0.1700

Data Index: 5745308 (Open Web Text)

Max Activating Token Index: 224

Text #11

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8387. Min Act: -0.1700

Data Index: 8448248 (Open Web Text)

Max Activating Token Index: 269

Text #12

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8337. Min Act: -0.1700

Data Index: 8403986 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8562. Min Act: -0.1700

Data Index: 7395554 (Open Web Text)

Max Activating Token Index: 276

Text #14

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8555. Min Act: -0.1700

Data Index: 6863983 (Open Web Text)

Max Activating Token Index: 842

Text #15

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8181. Min Act: -0.1700

Data Index: 648106 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8190. Min Act: -0.1700

Data Index: 3552738 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8144. Min Act: -0.1700

Data Index: 3574607 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8297. Min Act: -0.1700

Data Index: 3723970 (Open Web Text)

Max Activating Token Index: 340

Text #19

Max Range: 4.3618. Min Range: -4.3618

Max Act: 3.8164. Min Act: -0.1700

Data Index: 526287 (Open Web Text)

Max Activating Token Index: 239