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

Dataset: Open Web Text

Neuron 1668 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: 3.6333. Min Range: -3.6333

Max Act: 3.6333. Min Act: -0.1700

Data Index: 2497158 (Open Web Text)

Max Activating Token Index: 879

Text #1

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4684. Min Act: -0.1700

Data Index: 8059948 (Open Web Text)

Max Activating Token Index: 48

Text #2

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.4242. Min Act: -0.1700

Data Index: 3727085 (Open Web Text)

Max Activating Token Index: 351

Text #3

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3934. Min Act: -0.1700

Data Index: 4333881 (Open Web Text)

Max Activating Token Index: 922

Text #4

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3870. Min Act: -0.1700

Data Index: 7876162 (Open Web Text)

Max Activating Token Index: 305

Text #5

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3578. Min Act: -0.1700

Data Index: 5430818 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3291. Min Act: -0.1700

Data Index: 6781479 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3601. Min Act: -0.1700

Data Index: 2931949 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3807. Min Act: -0.1700

Data Index: 5209759 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3625. Min Act: -0.1700

Data Index: 3608191 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3363. Min Act: -0.1700

Data Index: 4284329 (Open Web Text)

Max Activating Token Index: 897

Text #11

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3575. Min Act: -0.1700

Data Index: 2854177 (Open Web Text)

Max Activating Token Index: 495

Text #12

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.2947. Min Act: -0.1700

Data Index: 2213630 (Open Web Text)

Max Activating Token Index: 602

Text #13

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3397. Min Act: -0.1700

Data Index: 4925104 (Open Web Text)

Max Activating Token Index: 814

Text #14

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3138. Min Act: -0.1700

Data Index: 1350500 (Open Web Text)

Max Activating Token Index: 623

Text #15

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3260. Min Act: -0.1700

Data Index: 4537667 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.2995. Min Act: -0.1700

Data Index: 4018258 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3144. Min Act: -0.1700

Data Index: 8141886 (Open Web Text)

Max Activating Token Index: 290

Text #18

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.2923. Min Act: -0.1700

Data Index: 8083932 (Open Web Text)

Max Activating Token Index: 482

Text #19

Max Range: 3.6333. Min Range: -3.6333

Max Act: 3.3375. Min Act: -0.1700

Data Index: 1514911 (Open Web Text)

Max Activating Token Index: 446