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

Dataset: Open Web Text

Neuron 1591 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: 5.3318. Min Range: -5.3318

Max Act: 5.3318. Min Act: -0.1700

Data Index: 3335271 (Open Web Text)

Max Activating Token Index: 742

Text #1

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.2708. Min Act: -0.1700

Data Index: 1687484 (Open Web Text)

Max Activating Token Index: 417

Text #2

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.2419. Min Act: -0.1700

Data Index: 6622963 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.2277. Min Act: -0.1700

Data Index: 8484571 (Open Web Text)

Max Activating Token Index: 38

Text #4

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.2055. Min Act: -0.1700

Data Index: 3747597 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1756. Min Act: -0.1700

Data Index: 2036842 (Open Web Text)

Max Activating Token Index: 160

Text #6

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1271. Min Act: -0.1700

Data Index: 2661751 (Open Web Text)

Max Activating Token Index: 621

Text #7

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1362. Min Act: -0.1700

Data Index: 3597505 (Open Web Text)

Max Activating Token Index: 824

Text #8

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1456. Min Act: -0.1700

Data Index: 2319810 (Open Web Text)

Max Activating Token Index: 331

Text #9

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1014. Min Act: -0.1700

Data Index: 666449 (Open Web Text)

Max Activating Token Index: 312

Text #10

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1115. Min Act: -0.1700

Data Index: 1727021 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1207. Min Act: -0.1700

Data Index: 8537853 (Open Web Text)

Max Activating Token Index: 574

Text #12

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.0991. Min Act: -0.1700

Data Index: 4261021 (Open Web Text)

Max Activating Token Index: 258

Text #13

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.0796. Min Act: -0.1700

Data Index: 8158642 (Open Web Text)

Max Activating Token Index: 949

Text #14

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1271. Min Act: -0.1700

Data Index: 7386864 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1374. Min Act: -0.1700

Data Index: 7183173 (Open Web Text)

Max Activating Token Index: 521

Text #16

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1208. Min Act: -0.1700

Data Index: 3772799 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1328. Min Act: -0.1700

Data Index: 6972030 (Open Web Text)

Max Activating Token Index: 615

Text #18

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.1105. Min Act: -0.1700

Data Index: 5273745 (Open Web Text)

Max Activating Token Index: 347

Text #19

Max Range: 5.3318. Min Range: -5.3318

Max Act: 5.0817. Min Act: -0.1700

Data Index: 37287 (Open Web Text)

Max Activating Token Index: 798