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

Dataset: Open Web Text

Neuron 2822 in Layer 3

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: 5.4171. Min Range: -5.4171

Max Act: 5.4171. Min Act: -0.1700

Data Index: 1336794 (Open Web Text)

Max Activating Token Index: 320

Text #1

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.3967. Min Act: -0.1700

Data Index: 1709052 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.3913. Min Act: -0.1700

Data Index: 7474666 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2875. Min Act: -0.1700

Data Index: 5688663 (Open Web Text)

Max Activating Token Index: 576

Text #4

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2624. Min Act: -0.1700

Data Index: 2045414 (Open Web Text)

Max Activating Token Index: 569

Text #5

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2524. Min Act: -0.1700

Data Index: 5984895 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2835. Min Act: -0.1700

Data Index: 2892455 (Open Web Text)

Max Activating Token Index: 928

Text #7

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2630. Min Act: -0.1700

Data Index: 2023261 (Open Web Text)

Max Activating Token Index: 180

Text #8

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2566. Min Act: -0.1700

Data Index: 1047810 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.1951. Min Act: -0.1700

Data Index: 496136 (Open Web Text)

Max Activating Token Index: 466

Text #10

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2061. Min Act: -0.1700

Data Index: 3451123 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2676. Min Act: -0.1700

Data Index: 2408169 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2246. Min Act: -0.1700

Data Index: 8511208 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2676. Min Act: -0.1700

Data Index: 616952 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2105. Min Act: -0.1700

Data Index: 7829018 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2452. Min Act: -0.1700

Data Index: 6395101 (Open Web Text)

Max Activating Token Index: 778

Text #16

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2767. Min Act: -0.1700

Data Index: 2840440 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2401. Min Act: -0.1700

Data Index: 7082803 (Open Web Text)

Max Activating Token Index: 765

Text #18

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.2234. Min Act: -0.1700

Data Index: 8390855 (Open Web Text)

Max Activating Token Index: 798

Text #19

Max Range: 5.4171. Min Range: -5.4171

Max Act: 5.1995. Min Act: -0.1700

Data Index: 5615834 (Open Web Text)

Max Activating Token Index: 147