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

Dataset: Open Web Text

Neuron 263 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: 4.6535. Min Range: -4.6535

Max Act: 4.6535. Min Act: -0.1700

Data Index: 8713980 (Open Web Text)

Max Activating Token Index: 901

Text #1

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.5978. Min Act: -0.1700

Data Index: 6351858 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.4970. Min Act: -0.1700

Data Index: 2822538 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.5021. Min Act: -0.1700

Data Index: 7495666 (Open Web Text)

Max Activating Token Index: 942

Text #4

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.4301. Min Act: -0.1700

Data Index: 5814285 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.4121. Min Act: -0.1700

Data Index: 7915345 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3995. Min Act: -0.1700

Data Index: 8248354 (Open Web Text)

Max Activating Token Index: 929

Text #7

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3594. Min Act: -0.1700

Data Index: 8107080 (Open Web Text)

Max Activating Token Index: 808

Text #8

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3821. Min Act: -0.1700

Data Index: 3897553 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3894. Min Act: -0.1700

Data Index: 4390043 (Open Web Text)

Max Activating Token Index: 103

Text #10

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.2780. Min Act: -0.1700

Data Index: 4436910 (Open Web Text)

Max Activating Token Index: 587

Text #11

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3289. Min Act: -0.1700

Data Index: 1811106 (Open Web Text)

Max Activating Token Index: 370

Text #12

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3410. Min Act: -0.1700

Data Index: 3258882 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3200. Min Act: -0.1700

Data Index: 210038 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3326. Min Act: -0.1700

Data Index: 314286 (Open Web Text)

Max Activating Token Index: 1013

Text #15

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3064. Min Act: -0.1700

Data Index: 2581613 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.3145. Min Act: -0.1700

Data Index: 6597556 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.2692. Min Act: -0.1700

Data Index: 2082631 (Open Web Text)

Max Activating Token Index: 709

Text #18

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.2965. Min Act: -0.1700

Data Index: 7755874 (Open Web Text)

Max Activating Token Index: 216

Text #19

Max Range: 4.6535. Min Range: -4.6535

Max Act: 4.2173. Min Act: -0.1700

Data Index: 4644587 (Open Web Text)

Max Activating Token Index: 742