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

Dataset: Open Web Text

Neuron 1660 in Layer 4

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: 3.3198. Min Range: -3.3198

Max Act: 3.3198. Min Act: -0.1700

Data Index: 7585309 (Open Web Text)

Max Activating Token Index: 458

Text #1

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1249026 (Open Web Text)

Max Activating Token Index: 560

Text #2

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.2163. Min Act: -0.1700

Data Index: 6401722 (Open Web Text)

Max Activating Token Index: 227

Text #3

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.1451. Min Act: -0.1700

Data Index: 2262234 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.1366. Min Act: -0.1700

Data Index: 3753566 (Open Web Text)

Max Activating Token Index: 690

Text #5

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.1337. Min Act: -0.1700

Data Index: 1845999 (Open Web Text)

Max Activating Token Index: 165

Text #6

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.1095. Min Act: -0.1700

Data Index: 8619228 (Open Web Text)

Max Activating Token Index: 686

Text #7

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0869. Min Act: -0.1700

Data Index: 5437625 (Open Web Text)

Max Activating Token Index: 450

Text #8

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0848. Min Act: -0.1700

Data Index: 3753565 (Open Web Text)

Max Activating Token Index: 22

Text #9

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0833. Min Act: -0.1700

Data Index: 3730445 (Open Web Text)

Max Activating Token Index: 619

Text #10

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0302. Min Act: -0.1700

Data Index: 6888720 (Open Web Text)

Max Activating Token Index: 309

Text #11

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0343. Min Act: -0.1700

Data Index: 1824395 (Open Web Text)

Max Activating Token Index: 163

Text #12

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0131. Min Act: -0.1700

Data Index: 514196 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 3.3198. Min Range: -3.3198

Max Act: 2.9765. Min Act: -0.1700

Data Index: 1453346 (Open Web Text)

Max Activating Token Index: 344

Text #14

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0137. Min Act: -0.1700

Data Index: 1811591 (Open Web Text)

Max Activating Token Index: 725

Text #15

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0202. Min Act: -0.1700

Data Index: 5464712 (Open Web Text)

Max Activating Token Index: 167

Text #16

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0004. Min Act: -0.1700

Data Index: 4687997 (Open Web Text)

Max Activating Token Index: 421

Text #17

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0318. Min Act: -0.1700

Data Index: 8283222 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 3.3198. Min Range: -3.3198

Max Act: 3.0126. Min Act: -0.1700

Data Index: 515551 (Open Web Text)

Max Activating Token Index: 179

Text #19

Max Range: 3.3198. Min Range: -3.3198

Max Act: 2.9795. Min Act: -0.1700

Data Index: 8659346 (Open Web Text)

Max Activating Token Index: 211