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

Dataset: Open Web Text

Neuron 2533 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: 3.4377. Min Range: -3.4377

Max Act: 3.4377. Min Act: -0.1700

Data Index: 1969204 (Open Web Text)

Max Activating Token Index: 844

Text #1

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3641. Min Act: -0.1700

Data Index: 5561438 (Open Web Text)

Max Activating Token Index: 709

Text #2

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3714. Min Act: -0.1700

Data Index: 4167082 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3365. Min Act: -0.1700

Data Index: 7150775 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3513. Min Act: -0.1700

Data Index: 1306224 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3099. Min Act: -0.1700

Data Index: 6989273 (Open Web Text)

Max Activating Token Index: 581

Text #6

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3244. Min Act: -0.1700

Data Index: 6214223 (Open Web Text)

Max Activating Token Index: 457

Text #7

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2930. Min Act: -0.1700

Data Index: 8522457 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.3172. Min Act: -0.1700

Data Index: 52435 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2790. Min Act: -0.1700

Data Index: 3492438 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2758. Min Act: -0.1700

Data Index: 6639654 (Open Web Text)

Max Activating Token Index: 747

Text #11

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2789. Min Act: -0.1700

Data Index: 8723013 (Open Web Text)

Max Activating Token Index: 200

Text #12

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2747. Min Act: -0.1700

Data Index: 1422586 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2992. Min Act: -0.1700

Data Index: 8433224 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2687. Min Act: -0.1700

Data Index: 6313706 (Open Web Text)

Max Activating Token Index: 308

Text #15

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2272. Min Act: -0.1700

Data Index: 2978777 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2625. Min Act: -0.1700

Data Index: 1219399 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2330. Min Act: -0.1700

Data Index: 2095209 (Open Web Text)

Max Activating Token Index: 800

Text #18

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2263. Min Act: -0.1700

Data Index: 1406378 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 3.4377. Min Range: -3.4377

Max Act: 3.2509. Min Act: -0.1700

Data Index: 2334748 (Open Web Text)

Max Activating Token Index: 250