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

Dataset: Open Web Text

Neuron 2074 in Layer 1

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: 3.1948. Min Range: -3.1948

Max Act: 3.1948. Min Act: -0.1700

Data Index: 2170951 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.1551. Min Act: -0.1700

Data Index: 842916 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.1258. Min Act: -0.1700

Data Index: 681837 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.1277. Min Act: -0.1700

Data Index: 3085927 (Open Web Text)

Max Activating Token Index: 61

Text #4

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.1296. Min Act: -0.1700

Data Index: 5889147 (Open Web Text)

Max Activating Token Index: 111

Text #5

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0779. Min Act: -0.1700

Data Index: 2640958 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0688. Min Act: -0.1700

Data Index: 5078130 (Open Web Text)

Max Activating Token Index: 224

Text #7

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0609. Min Act: -0.1700

Data Index: 4705113 (Open Web Text)

Max Activating Token Index: 395

Text #8

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0686. Min Act: -0.1700

Data Index: 1418224 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0686. Min Act: -0.1700

Data Index: 6568036 (Open Web Text)

Max Activating Token Index: 202

Text #10

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0733. Min Act: -0.1700

Data Index: 7322084 (Open Web Text)

Max Activating Token Index: 554

Text #11

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0610. Min Act: -0.1700

Data Index: 2391428 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0753. Min Act: -0.1700

Data Index: 5550723 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0432. Min Act: -0.1700

Data Index: 8524587 (Open Web Text)

Max Activating Token Index: 888

Text #14

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0327. Min Act: -0.1700

Data Index: 3206822 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0307. Min Act: -0.1700

Data Index: 5558003 (Open Web Text)

Max Activating Token Index: 628

Text #16

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0206. Min Act: -0.1700

Data Index: 1493822 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0308. Min Act: -0.1700

Data Index: 2268507 (Open Web Text)

Max Activating Token Index: 646

Text #18

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0323. Min Act: -0.1700

Data Index: 6149711 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 3.1948. Min Range: -3.1948

Max Act: 3.0274. Min Act: -0.1700

Data Index: 159701 (Open Web Text)

Max Activating Token Index: 898