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

Dataset: Open Web Text

Neuron 2058 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: 1.1734. Min Range: -1.1734

Max Act: 1.1642. Min Act: -0.1700

Data Index: 2177296 (Open Web Text)

Max Activating Token Index: 308

Text #1

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1734. Min Act: -0.1700

Data Index: 4100456 (Open Web Text)

Max Activating Token Index: 323

Text #2

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1608. Min Act: -0.1700

Data Index: 7055532 (Open Web Text)

Max Activating Token Index: 308

Text #3

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1350. Min Act: -0.1700

Data Index: 6760769 (Open Web Text)

Max Activating Token Index: 322

Text #4

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1305. Min Act: -0.1700

Data Index: 2117981 (Open Web Text)

Max Activating Token Index: 295

Text #5

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1430. Min Act: -0.1700

Data Index: 1299347 (Open Web Text)

Max Activating Token Index: 311

Text #6

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1330. Min Act: -0.1700

Data Index: 3394721 (Open Web Text)

Max Activating Token Index: 303

Text #7

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1244. Min Act: -0.1700

Data Index: 839777 (Open Web Text)

Max Activating Token Index: 315

Text #8

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1296. Min Act: -0.1700

Data Index: 4878690 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1247. Min Act: -0.1700

Data Index: 8501615 (Open Web Text)

Max Activating Token Index: 319

Text #10

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1299. Min Act: -0.1700

Data Index: 8096423 (Open Web Text)

Max Activating Token Index: 311

Text #11

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1282. Min Act: -0.1700

Data Index: 4790593 (Open Web Text)

Max Activating Token Index: 315

Text #12

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1294. Min Act: -0.1700

Data Index: 216679 (Open Web Text)

Max Activating Token Index: 313

Text #13

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1235. Min Act: -0.1700

Data Index: 6783542 (Open Web Text)

Max Activating Token Index: 292

Text #14

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1481. Min Act: -0.1700

Data Index: 20537 (Open Web Text)

Max Activating Token Index: 315

Text #15

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1204. Min Act: -0.1700

Data Index: 2920092 (Open Web Text)

Max Activating Token Index: 300

Text #16

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1289. Min Act: -0.1700

Data Index: 520829 (Open Web Text)

Max Activating Token Index: 304

Text #17

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1062. Min Act: -0.1700

Data Index: 4914996 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1214. Min Act: -0.1700

Data Index: 5333569 (Open Web Text)

Max Activating Token Index: 301

Text #19

Max Range: 1.1734. Min Range: -1.1734

Max Act: 1.1065. Min Act: -0.1700

Data Index: 6044927 (Open Web Text)

Max Activating Token Index: 305