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

Dataset: Open Web Text

Neuron 685 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: 5.9097. Min Range: -5.9097

Max Act: 5.9097. Min Act: -0.1700

Data Index: 2546363 (Open Web Text)

Max Activating Token Index: 486

Text #1

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.7864. Min Act: -0.1700

Data Index: 38335 (Open Web Text)

Max Activating Token Index: 288

Text #2

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.6916. Min Act: -0.1700

Data Index: 3564466 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.6103. Min Act: -0.1700

Data Index: 2618845 (Open Web Text)

Max Activating Token Index: 453

Text #4

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.3427. Min Act: -0.1700

Data Index: 2707567 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2585. Min Act: -0.1700

Data Index: 7200649 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2735. Min Act: -0.1700

Data Index: 4984992 (Open Web Text)

Max Activating Token Index: 130

Text #7

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2396. Min Act: -0.1700

Data Index: 6746503 (Open Web Text)

Max Activating Token Index: 858

Text #8

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2025. Min Act: -0.1700

Data Index: 8544432 (Open Web Text)

Max Activating Token Index: 181

Text #9

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2549. Min Act: -0.1700

Data Index: 4850774 (Open Web Text)

Max Activating Token Index: 370

Text #10

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2201. Min Act: -0.1700

Data Index: 4806334 (Open Web Text)

Max Activating Token Index: 274

Text #11

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1892. Min Act: -0.1700

Data Index: 8172079 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1846. Min Act: -0.1700

Data Index: 2510875 (Open Web Text)

Max Activating Token Index: 294

Text #13

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.2051. Min Act: -0.1700

Data Index: 3050298 (Open Web Text)

Max Activating Token Index: 503

Text #14

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1778. Min Act: -0.1700

Data Index: 1579664 (Open Web Text)

Max Activating Token Index: 317

Text #15

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1872. Min Act: -0.1700

Data Index: 2319588 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1307. Min Act: -0.1700

Data Index: 869160 (Open Web Text)

Max Activating Token Index: 397

Text #17

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1885. Min Act: -0.1700

Data Index: 5711759 (Open Web Text)

Max Activating Token Index: 692

Text #18

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1413. Min Act: -0.1700

Data Index: 4453424 (Open Web Text)

Max Activating Token Index: 960

Text #19

Max Range: 5.9097. Min Range: -5.9097

Max Act: 5.1470. Min Act: -0.1700

Data Index: 6324464 (Open Web Text)

Max Activating Token Index: 291