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

Dataset: Open Web Text

Neuron 999 in Layer 2

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: 4.7338. Min Range: -4.7338

Max Act: 4.7338. Min Act: -0.1700

Data Index: 1324663 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.5296. Min Act: -0.1700

Data Index: 6832825 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.3507. Min Act: -0.1700

Data Index: 4140155 (Open Web Text)

Max Activating Token Index: 615

Text #3

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.3587. Min Act: -0.1700

Data Index: 3710113 (Open Web Text)

Max Activating Token Index: 248

Text #4

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.3876. Min Act: -0.1700

Data Index: 8655485 (Open Web Text)

Max Activating Token Index: 324

Text #5

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2747. Min Act: -0.1700

Data Index: 5752961 (Open Web Text)

Max Activating Token Index: 51

Text #6

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2776. Min Act: -0.1700

Data Index: 6841327 (Open Web Text)

Max Activating Token Index: 954

Text #7

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2724. Min Act: -0.1700

Data Index: 6164819 (Open Web Text)

Max Activating Token Index: 309

Text #8

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2752. Min Act: -0.1700

Data Index: 2014621 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2366. Min Act: -0.1700

Data Index: 8301357 (Open Web Text)

Max Activating Token Index: 439

Text #10

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2320. Min Act: -0.1700

Data Index: 1364223 (Open Web Text)

Max Activating Token Index: 67

Text #11

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2166. Min Act: -0.1700

Data Index: 2383417 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2009. Min Act: -0.1700

Data Index: 7125991 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2169. Min Act: -0.1700

Data Index: 2149917 (Open Web Text)

Max Activating Token Index: 450

Text #14

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2116. Min Act: -0.1700

Data Index: 434927 (Open Web Text)

Max Activating Token Index: 939

Text #15

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.1991. Min Act: -0.1700

Data Index: 2268305 (Open Web Text)

Max Activating Token Index: 622

Text #16

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2078. Min Act: -0.1700

Data Index: 2857418 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.2461. Min Act: -0.1700

Data Index: 4143178 (Open Web Text)

Max Activating Token Index: 684

Text #18

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.1618. Min Act: -0.1700

Data Index: 1939807 (Open Web Text)

Max Activating Token Index: 402

Text #19

Max Range: 4.7338. Min Range: -4.7338

Max Act: 4.1531. Min Act: -0.1700

Data Index: 2378342 (Open Web Text)

Max Activating Token Index: 224