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

Dataset: Open Web Text

Neuron 1271 in Layer 6

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: 4.4257. Min Range: -4.4257

Max Act: 4.4257. Min Act: -0.1700

Data Index: 4297454 (Open Web Text)

Max Activating Token Index: 614

Text #1

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.2969. Min Act: -0.1700

Data Index: 1754054 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.3427. Min Act: -0.1700

Data Index: 6375187 (Open Web Text)

Max Activating Token Index: 820

Text #3

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.2617. Min Act: -0.1700

Data Index: 3360036 (Open Web Text)

Max Activating Token Index: 228

Text #4

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.2527. Min Act: -0.1700

Data Index: 3044951 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1937. Min Act: -0.1700

Data Index: 8736700 (Open Web Text)

Max Activating Token Index: 936

Text #6

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1860. Min Act: -0.1700

Data Index: 8543701 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.2184. Min Act: -0.1700

Data Index: 4677669 (Open Web Text)

Max Activating Token Index: 781

Text #8

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1731. Min Act: -0.1700

Data Index: 4640935 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1543. Min Act: -0.1700

Data Index: 5530194 (Open Web Text)

Max Activating Token Index: 936

Text #10

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1305. Min Act: -0.1700

Data Index: 287004 (Open Web Text)

Max Activating Token Index: 988

Text #11

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1538. Min Act: -0.1700

Data Index: 6311315 (Open Web Text)

Max Activating Token Index: 693

Text #12

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1651. Min Act: -0.1700

Data Index: 989248 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1613. Min Act: -0.1700

Data Index: 446065 (Open Web Text)

Max Activating Token Index: 238

Text #14

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1227. Min Act: -0.1700

Data Index: 7138838 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1553. Min Act: -0.1700

Data Index: 6573804 (Open Web Text)

Max Activating Token Index: 84

Text #16

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1828. Min Act: -0.1700

Data Index: 5134396 (Open Web Text)

Max Activating Token Index: 634

Text #17

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1331. Min Act: -0.1700

Data Index: 931770 (Open Web Text)

Max Activating Token Index: 35

Text #18

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1393. Min Act: -0.1700

Data Index: 8157223 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.4257. Min Range: -4.4257

Max Act: 4.1659. Min Act: -0.1700

Data Index: 8394999 (Open Web Text)

Max Activating Token Index: 168