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

Dataset: Open Web Text

Neuron 2789 in Layer 5

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: 3.2318. Min Range: -3.2318

Max Act: 3.2318. Min Act: -0.1700

Data Index: 5467575 (Open Web Text)

Max Activating Token Index: 106

Text #1

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1783. Min Act: -0.1700

Data Index: 1759362 (Open Web Text)

Max Activating Token Index: 262

Text #2

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1904. Min Act: -0.1700

Data Index: 2399160 (Open Web Text)

Max Activating Token Index: 436

Text #3

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1768. Min Act: -0.1700

Data Index: 4177674 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1765. Min Act: -0.1700

Data Index: 121418 (Open Web Text)

Max Activating Token Index: 468

Text #5

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1557. Min Act: -0.1700

Data Index: 1608702 (Open Web Text)

Max Activating Token Index: 67

Text #6

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1218. Min Act: -0.1700

Data Index: 2771662 (Open Web Text)

Max Activating Token Index: 116

Text #7

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1243. Min Act: -0.1700

Data Index: 7012079 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1229. Min Act: -0.1700

Data Index: 399570 (Open Web Text)

Max Activating Token Index: 495

Text #9

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1157. Min Act: -0.1700

Data Index: 3068651 (Open Web Text)

Max Activating Token Index: 772

Text #10

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1304. Min Act: -0.1700

Data Index: 7001396 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.1138. Min Act: -0.1700

Data Index: 1905132 (Open Web Text)

Max Activating Token Index: 696

Text #12

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0950. Min Act: -0.1700

Data Index: 7626105 (Open Web Text)

Max Activating Token Index: 355

Text #13

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0798. Min Act: -0.1700

Data Index: 4897441 (Open Web Text)

Max Activating Token Index: 245

Text #14

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0647. Min Act: -0.1700

Data Index: 8603944 (Open Web Text)

Max Activating Token Index: 760

Text #15

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0961. Min Act: -0.1700

Data Index: 1516664 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0797. Min Act: -0.1700

Data Index: 6148335 (Open Web Text)

Max Activating Token Index: 1003

Text #17

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0876. Min Act: -0.1700

Data Index: 1483686 (Open Web Text)

Max Activating Token Index: 323

Text #18

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0785. Min Act: -0.1700

Data Index: 6654072 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 3.2318. Min Range: -3.2318

Max Act: 3.0764. Min Act: -0.1700

Data Index: 5606992 (Open Web Text)

Max Activating Token Index: 215